Enrichment Analysis for Deiodinase Activity

For full transparency and reproducibility, this Rmd file shows all the enrichment calculations performed and their results for completeness. This can be found as a Supplemental File under Truong et al. (in preparation).

Data Import and Environment

rm(list=ls())
library(data.table)
library(dplyr)
library(tidyr)
library(ggplot2)
library(ggrepel)
library(ggvenn)
library(cowplot)
library(viridis)
library(RColorBrewer)
library(colorspace)
library(scales)
library(ggpubr)
library(openxlsx)
library(readxl)

load('./data/invitrodb_v3_5_thyroid_data.RData', verbose = T)

## Loading objects:
##   ace
##   ace.thyroid
##   cytotox
##   gene
##   mc5
##   mc5.hitc1
##   sc1
##   sc2

# create a `not in` operator
`%notin%` <- Negate(`%in%`)

Overview of Classes

meta data

# DIO/IYD assays
deiod.meta <- ace.thyroid[thyroid_related_target == 'Deiodinases', 
                          .(aeid, aenm = assay_component_endpoint_name)]

aenm.abbrevs <- c('DIO1', 'DIO2', 'DIO3', 'IYD')

# ignore amphibian assays 
h.deiod.aeids <- deiod.meta[grepl("\\w+h(DIO|IYD)\\w+", deiod.meta$aenm), aeid]
h.deiod.aenm <- deiod.meta[grepl("\\w+h(DIO|IYD)\\w+", deiod.meta$aenm), aenm]
names(h.deiod.aeids) <- aenm.abbrevs
names(h.deiod.aenm) <- aenm.abbrevs

Hitcall Matrix

# get hitcall data from sc/mc for DIO/IYD assays 
long.mc5 <- mc5[!is.na(dsstox_substance_id) & aeid %in% h.deiod.aeids, 
                .(dsstox_substance_id, aenm, hitc)]
long.sc2 <- sc2[!is.na(dsstox_substance_id) & aeid %in% h.deiod.aeids, 
                .(dsstox_substance_id, aenm, hitc)]

# combine mc/sc data
long_all <- merge.data.table(long.sc2, long.mc5, 
                             by = c("dsstox_substance_id", "aenm"), 
                             all = T)
setnames(long_all, old = c("hitc.x", "hitc.y"), 
         new = c("sc.hitc", "mc.hitc"))

# if tested in both, take hitc from mc; otherwise, take hitc from sc 
long_hitc_final <- long_all %>% 
  rowwise() %>%
  mutate(hitc = ifelse(!is.na(mc.hitc), mc.hitc, sc.hitc))

# form a hitcall matrix of all 2007 tested chems 
M.hitc <- long_hitc_final %>% 
  select(dsstox_substance_id, aenm, hitc) %>% 
  pivot_wider(names_from = aenm, values_from = hitc) %>% 
  as.data.frame()

M.hitc$chnm <- sc2$chnm[match(M.hitc$dsstox_substance_id, sc2$dsstox_substance_id)]
M.hitc <- M.hitc[, c("dsstox_substance_id", "chnm", h.deiod.aenm)]

row.names(M.hitc) <- M.hitc$dsstox_substance_id
M.hitc <- M.hitc[, -1]

Hitcall Distribution

# load updated classifications from Richard - 9/5/23
new.classified <- read_excel(file.path("./data", "chem_classifications.xlsx")) %>% 
  as.data.table()

# move subset of QACs from "Expert" to "ClassyFire" group
new.classified[class_type == "Expert" & chosen_class == "Quaternary ammonium salts", class_type := "ClassyFire"]

# subset down to DIO/IYD test chems 
classified_dt <- new.classified[dtxsid %in% rownames(M.hitc)]
setnames(classified_dt, "dtxsid", "dsstox_substance_id")

# match chemical order with M.hitc for 1-1 correspondence 
classified_dt <- classified_dt[match(rownames(M.hitc), classified_dt$dsstox_substance_id), ]
identical(rownames(M.hitc), classified_dt$dsstox_substance_id)

## [1] TRUE

counts <- classified_dt[, .N, keyby = .(class_type, chosen_class)][
  order(-N), .SD, keyby = .(class_type)
]

setDT(long_hitc_final)

# add selectivity as a column to long_hitc_final for better interpretation of hits 
mc.deiod <- mc5[aeid %in% h.deiod.aeids & !is.na(dsstox_substance_id), .(chnm, aenm, modl_acc, modl_ga), 
                by = .(aeid, dsstox_substance_id)]
mc.deiod[is.na(modl_acc), modl_acc := 5]
mc.deiod$cytomed <- cytotox$cytotox_median_log[match(mc.deiod$dsstox_substance_id, cytotox$dsstox_substance_id)]

# positive controls for DIO2/3/IYD are missing cytotox points 
mc.deiod[is.na(cytomed)]

mc.deiod[is.na(cytomed), cytomed := 3]
mc.deiod[, selectivity := cytomed - pmin(modl_acc, 5)]

Impute cytotox median AC50 values for Xanthohumol and 3-Nitro-L-tyrosine to 3 (log10 uM).

long_hitc_final2 <- merge.data.table(long_hitc_final, 
                                     mc.deiod[, .(dsstox_substance_id, aenm, modl_acc, modl_ga, selectivity)], 
                                     by = c("dsstox_substance_id", "aenm"), 
                                     all.x = T)

# use selectivity as a stricter threshold for hitcall determination 
long_hitc_final2[selectivity < 0.3, hitc := 0]

# merging hitcalls with class information
merged_dat <- merge.data.table(long_hitc_final, 
                               classified_dt[, .(dsstox_substance_id, name, class_type, chosen_class)], 
                               by = c("dsstox_substance_id"), 
                               all.x = T)

for (i in 1:length(h.deiod.aenm)) {
  merged_dat[aenm == h.deiod.aenm[i], assay := names(h.deiod.aenm)[i] ]
}

# total number of chems tested in each assay (before classification)
merged_dat[, Nchems := length(dsstox_substance_id), keyby = aenm]
setnames(merged_dat, "Nchems", "Ntested")

# How many were classified in each assay? should be ALL thx to Richard 
merged_dat[!is.na(chosen_class), .( Nclassified = length(dsstox_substance_id) ), 
           keyby = aenm]

# distribution of pos/neg chems with classifications for each assay
hitc.dist <- merged_dat[, .( numChems = length(dsstox_substance_id) ), 
           keyby = .(aenm, Ntested, hitc)]
hitc.dist[, hitrate := numChems/Ntested, by = .(aenm, hitc)]
hitc.dist

100% classified with new classification scheme.

Class Composition by Assay

The top 25 classes (or groups of classes) for each chemical library are shown here. Classes that made up less than 1% of the library for that assay shown here were regrouped into a broader and related “Other [classes from Classyfire|Drugs|Expert chemicals|Pesticides|PFAS categories]” category.

# distribution of classes for test libraries 
counts.by.aenm <- merged_dat[, .( .N ), keyby = .(aenm, class_type, chosen_class)]

# sorted by counts from highest to lowest, grouped by aenm 
counts.by.aenm <- counts.by.aenm[order(-N), .SD, by = aenm]

# compute percentages per assay
counts.by.aenm[, total := sum(N), by = aenm]
counts.by.aenm[, fraction := N/total, by = .(aenm, chosen_class)]

# for classes with < 1% of chems, group them as 'Other (class_type)'
other_rows <- counts.by.aenm[fraction < 0.01,
                             .( chosen_class = paste("Other", class_type, sep = " "),
                                N = sum(N),
                                total = .SD[1, total], # denominator stays the same 
                                fraction = sum(fraction)),
                             by = .(aenm, class_type)]

# relabel into broader categories
other_rows[chosen_class == "Other ClassyFire", chosen_class := "Other classes from ClassyFire"]
other_rows[chosen_class == "Other Pesticide", chosen_class := "Other Pesticides"]
other_rows[chosen_class == "Other Expert", chosen_class := "Other Expert chemicals"]
other_rows[chosen_class == "Other Drug", chosen_class := "Other Drugs"]
other_rows[chosen_class == "Other PFAS", chosen_class := "Other PFAS categories"]
other_rows[chosen_class == "Other Color", chosen_class := "Other colors"]

# append these rows and resort
counts.by.aenm <- rbindlist(list(counts.by.aenm, other_rows))
counts.by.aenm <- counts.by.aenm[order(-N), .SD, keyby = aenm]

# specify hole size for donut chart 
hsize <- 3 
counts.by.aenm[, x := hsize]
counts.by.aenm$aeid <- deiod.meta$aeid[match(counts.by.aenm$aenm, deiod.meta$aenm)]

# collect ggplot objects for ggpubr
plot_list <- list()

# form palette for top 25 classes from each ae
classes_to_plot <- counts.by.aenm[1:25, .SD, by = aenm][, unique(chosen_class)]
n.classes <- length(classes_to_plot)
class_pal <- c(brewer.pal(n = 12, name = "Set3"), qualitative_hcl(n.classes-12, palette = "set2"))

# to maintain consistent class-to-color map across subplots 
counts.by.aenm$chosen_class <- as.factor(counts.by.aenm$chosen_class)
class_pal <- setNames(class_pal, classes_to_plot)

for(i in 1:4) {
  plot_list[[ names(h.deiod.aeids)[i] ]] <- ggplot(counts.by.aenm[aeid == h.deiod.aeids[i]][1:25], aes(x = hsize, y = fraction, fill = chosen_class)) +
    geom_col(color = 'black') +
    geom_label_repel(aes(label = N), 
                     size = 7, 
                     position = position_stack(vjust = 0.5),
                     show.legend = FALSE, 
                     force_pull = 10) +
    scale_fill_manual(values = class_pal) +
    xlim(c(0.2, hsize + 0.5)) +
    coord_polar(theta = "y") +
    theme_void() +
    ggtitle(names(h.deiod.aeids)[i]) +
    theme(
      legend.title = element_text(size = 20), 
      legend.text = element_text(size = 20), 
      plot.title = element_text(size = 20)
    )
}

plot_list[["DIO1"]] <- plot_list[["DIO1"]] + guides(fill = guide_legend(nrow = 9, ncol = 3))

# combine the plots into one figure
class.comp <- ggarrange(plot_list$DIO1, plot_list$IYD,
                    plot_list$DIO2, plot_list$DIO3, 
                    ncol = 2, nrow = 2, 
                    common.legend = TRUE, 
                    legend = 'bottom')
class.comp

# ggsave(plot = class.comp,
#        units = "in",
#        dpi = 72,
#        width = 20, height = 14,
#        device = "jpg",
#        filename = "./doc/comptox-thyroid-httk/figures/supp/DIO_IYD_chem_library_composition.jpg")

Class Enrichment

Run Fisher’s test for every assay x class

# form hitcall and class matrix 
M.hitc2 <- M.hitc[, h.deiod.aenm] # take all assay columns 
M.class <- as.data.frame.matrix(table(classified_dt$dsstox_substance_id, 
                                           classified_dt$chosen_class))

# check that rows are ordered the same 
identical(rownames(M.hitc2), rownames(M.class))

## [1] TRUE

RunFisherTests <- function(M.hitc, M.ident, cf_level) {
  
  dfList <- list()
  num.aeids <- ncol(M.hitc)
  
  # run tests only on classes of sufficient size (n >= 3)
  cs = colSums(M.ident)
  col.ind <- which(cs >= 3)
  
  for(i in 1:num.aeids) {
    dataft <- matrix(NA, ncol = 8, nrow = length(col.ind))
    
    for(j in 1:length(col.ind)) {
      
      # calculate entries of 2x2 table 
      a <- sum(M.ident[, col.ind[[j]] ] * M.hitc[, i], na.rm = T)
      b <- sum(M.ident[, col.ind[[j]] ] * (1 - M.hitc[, i]), na.rm = T)
      c <- sum( (1 - M.ident[, col.ind[[j]] ]) * M.hitc[, i], na.rm = T)
      d <- sum( (1 - M.ident[, col.ind[[j]] ]) * (1 - M.hitc[, i]), na.rm = T)
      
      tf <- data.frame("active" = c(a,c), "inactive" = c(b, d),
                       row.names = paste(c('in', 'not in'), cf_level))
      
      fttf<- fisher.test(tf)
      
      dataft[j,] <- c(fttf$p.value, fttf$estimate, fttf$conf.int, a, b, c, d)
      
    }
    
    # construct the dataframe for each assay  
    ft.outputs <- c("Pval","Odds_Ratio","Lower","Upper")
    ft.cells <- paste0(c('Actives in ', 'Inactives in ', 'Actives not in ', 'Inactives not in '), cf_level)
    
    colnames(dataft) <- c(ft.outputs, ft.cells)
    
    dataft<-data.frame(dataft, check.names = FALSE)
    
    dataft$padj<-p.adjust(dataft$Pval, method="fdr")
    dataft[, cf_level] <- names(col.ind)
    
    dataft <- dataft[, c(1:4,9,10,5:8)]
    
    dfList[[i]] <- dataft
  }
  
  # reorder rows by most significant results with OR
  dfList = lapply(dfList, function(x) arrange(x, padj, desc(Odds_Ratio)))
  
  return(dfList)
}

res <- RunFisherTests(M.hitc2, M.class, 'group')

DIO1

For DIO1

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0000231	42.7111064	5.1495406	1950.4429047	0.0033800	Estrogen flavonoid	6	1	240	1715
0.0000386	16.6762417	3.7765575	100.7212331	0.0033800	Quaternary ammonium salts	7	3	239	1713
0.0000826	21.3614515	3.7924053	216.9455955	0.0048163	Herbicide Chloroacetamide Very Long-Chain Fatty Acid Synthesis inhibitor	6	2	240	1714
0.0004964	10.6736721	2.5112253	51.8308497	0.0217192	Estrogen nonsteroidal	6	4	240	1712
0.0010899	28.2448681	2.7815095	1384.8677637	0.0317886	Antibiotic polyketide	4	1	242	1715
0.0010899	28.2448681	2.7815095	1384.8677637	0.0317886	Insecticide Arylalkyl organothiophosphate AChE Inhibitor	4	1	242	1715
0.0019501	Inf	2.8965972	Inf	0.0426586	Aryl chlorides	3	0	243	1716
0.0019501	Inf	2.8965972	Inf	0.0426586	Fungicide Phthalimide Multi-site activity	3	0	243	1716
0.0072497	5.9037294	1.4138688	23.4145767	0.1153357	Bisphenol	5	6	241	1710
0.0068402	4.7357105	1.3742904	15.0520307	0.1153357	Insecticide Aryl organothiophosphate AChE Inhibitor	6	9	240	1707
0.0070574	0.0000000	0.0000000	0.6466012	0.1153357	Carbonyl compounds	0	41	246	1675
0.0260963	0.0000000	0.0000000	0.9043474	0.3805717	Alcohols and polyols	0	30	246	1686
0.0430942	14.0219320	0.7274453	824.9556901	0.3969199	Anilides	2	1	244	1715
0.0430942	14.0219320	0.7274453	824.9556901	0.3969199	Lineolic acids and derivatives	2	1	244	1715
0.0430942	14.0219320	0.7274453	824.9556901	0.3969199	Organometallic Hg	2	1	244	1715
0.0430942	14.0219320	0.7274453	824.9556901	0.3969199	Retinoid	2	1	244	1715
0.0430942	14.0219320	0.7274453	824.9556901	0.3969199	Thyroid hormone	2	1	244	1715
0.0430942	14.0219320	0.7274453	824.9556901	0.3969199	Tryptase inhibitor	2	1	244	1715
0.0389029	4.0313648	0.8588912	15.9935326	0.3969199	Sulfuric acid esters	4	7	242	1709
0.0463707	5.2765205	0.7683196	31.4089393	0.4057435	PFAA precursors	3	4	243	1712
0.0527664	3.5251843	0.7709891	13.2794249	0.4397199	1-hydroxy-2-unsubstituted benzenoids	4	8	242	1708
0.0574597	2.2723631	0.8755678	5.2720346	0.4570660	PFAAs	8	25	238	1691
0.0791136	7.0123087	0.5061477	97.1838883	0.5768699	HMGCoA inhibitor	2	2	244	1714
0.0791136	7.0123087	0.5061477	97.1838883	0.5768699	PPARg agonist	2	2	244	1714
0.0978861	0.0000000	0.0000000	1.3339212	0.6852027	Fungicide Triazole Sterol Biosynthesis in Membranes	0	21	246	1695
0.1051428	1.6649982	0.8452681	3.0747380	0.7076916	Other aliphatics	14	60	232	1656
0.1211546	4.6745339	0.3886038	40.9669562	0.7562077	Antiviral	2	3	244	1713
0.1198537	3.0116558	0.4992440	13.3048425	0.7562077	Polymer unclassified	3	7	243	1709
0.1253144	1.9546020	0.7629369	4.4473285	0.7562077	Unclassed	8	29	238	1687
0.1671538	3.5045293	0.3154710	24.6013135	0.8807429	Benzothiazoles	2	4	244	1712
0.1671538	3.5045293	0.3154710	24.6013135	0.8807429	COX inhibitor	2	4	244	1712
0.1656632	0.2461696	0.0059969	1.5031031	0.8807429	Carboxylic acid derivatives	1	28	245	1688
0.1711158	0.2219552	0.0054252	1.3446220	0.8807429	Monoterpenoids	1	31	245	1685
0.1531528	0.0000000	0.0000000	1.5824389	0.8807429	Organosilicon compounds	0	18	246	1698
0.3311025	3.4943266	0.0590515	67.4562505	1.0000000	Benzenediols	1	2	245	1714
0.3311025	3.4943266	0.0590515	67.4562505	1.0000000	Benzenesulfonyl compounds	1	2	245	1714
0.3311025	3.4943266	0.0590515	67.4562505	1.0000000	Fungicide Anilinopyrimidine Amino Acid and Protein Synthesis	1	2	245	1714
0.3311025	3.4943266	0.0590515	67.4562505	1.0000000	Fungicide Imidazole Sterol Biosynthesis in Membranes	1	2	245	1714
0.3311025	3.4943266	0.0590515	67.4562505	1.0000000	Fungicide Thiocarbamate Multi-site activity	1	2	245	1714
0.3311025	3.4943266	0.0590515	67.4562505	1.0000000	Herbicide Triazolopyrimidine Acetolactate synthase inhibitor	1	2	245	1714
0.3311025	3.4943266	0.0590515	67.4562505	1.0000000	Phenanthrenes and derivatives	1	2	245	1714
0.3311025	3.4943266	0.0590515	67.4562505	1.0000000	Vinyl chlorides	1	2	245	1714
0.2154671	2.8028199	0.2655255	17.2318761	1.0000000	Antifungal	2	5	244	1711
0.2154671	2.8028199	0.2655255	17.2318761	1.0000000	Azobenzenes	2	5	244	1711
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Adrenergic beta agonist	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Androgen nonsteroidal antagonist	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Benzofuranones	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Biphenyls and derivatives	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	FASA based PFAA precursors	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Glyceryl	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Halopyridines	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Herbicide N-Phenylimide Protoporphyrinogen Oxidase inhibitor	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Phenylmethylamines	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Serotonin receptor antagonist	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Side-chain aromatics	1	3	245	1713
0.4150988	2.3292572	0.0442163	29.1400687	1.0000000	Triazoles	1	3	245	1713
0.3033204	1.7555792	0.4236236	5.5029800	1.0000000	Fatty acids and conjugates	4	16	242	1700
0.4885849	1.7463273	0.0353301	17.7357118	1.0000000	Pyrrolidones	1	4	245	1712
0.2927271	1.5634650	0.5223738	3.9186390	1.0000000	Phenylpropanes	6	27	240	1689
0.5528711	1.3964615	0.0294122	12.5543164	1.0000000	Androgen	1	5	245	1711
0.5528711	1.3964615	0.0294122	12.5543164	1.0000000	Antifungal paraben	1	5	245	1711
0.5528711	1.3964615	0.0294122	12.5543164	1.0000000	Cumenes	1	5	245	1711
0.5528711	1.3964615	0.0294122	12.5543164	1.0000000	Diphenylethers	1	5	245	1711
0.5528711	1.3964615	0.0294122	12.5543164	1.0000000	Insecticide Organophosphate AChE Inhibitor	1	5	245	1711
0.5528711	1.3964615	0.0294122	12.5543164	1.0000000	Isoindolines	1	5	245	1711
0.5528711	1.3964615	0.0294122	12.5543164	1.0000000	Naphthols and derivatives	1	5	245	1711
0.6729907	1.2703218	0.1360581	5.8721892	1.0000000	Insecticide Carbamate AChE Inhibitor	2	11	244	1705
0.6921051	1.1638247	0.1257564	5.2750657	1.0000000	Amino acids, peptides, and analogues	2	12	244	1704
1.0000000	1.1631568	0.0251881	9.6495391	1.0000000	Benzophenones	1	6	245	1710
1.0000000	1.1631568	0.0251881	9.6495391	1.0000000	Insecticide Organochlorine Sodium channel modulator	1	6	245	1710
1.0000000	0.9965032	0.0220218	7.8100757	1.0000000	Benzenesulfonic acids and derivatives	1	7	245	1709
1.0000000	0.9965032	0.0220218	7.8100757	1.0000000	Herbicide Dinitroaniline Microtubule assembly inhibitor	1	7	245	1709
1.0000000	0.9964889	0.1092701	4.3796481	1.0000000	Insecticide Pyrethroid Sodium channel modulator	2	14	244	1702
1.0000000	0.9295322	0.1025357	4.0358158	1.0000000	Nitrobenzenes	2	15	244	1701
1.0000000	0.8714592	0.0195600	6.5474555	1.0000000	Halophenols	1	8	245	1708
1.0000000	0.8714592	0.0195600	6.5474555	1.0000000	Herbicide Aryloxyphenoxypropionic Acetyl CoA carboxylase inhibitor	1	8	245	1708
1.0000000	0.8714592	0.0195600	6.5474555	1.0000000	Insecticide Chlorinated cyclodiene GABA-gated chloride channel blocker	1	8	245	1708
0.8112857	0.7501553	0.1925318	2.1152422	1.0000000	Benzoic acids and derivatives	4	37	242	1679
1.0000000	0.6964391	0.0159808	4.9334381	1.0000000	Cresols	1	10	245	1706
1.0000000	0.6964391	0.0159808	4.9334381	1.0000000	Insecticide Aliphatic organothiophosphate AChE Inhibitor	1	10	245	1706
0.7923622	0.6711660	0.1303103	2.1769729	1.0000000	Fatty acid esters	3	31	243	1685
0.7606135	0.6034797	0.0685457	2.4677036	1.0000000	Pharmaceutical unknown MOA	2	23	244	1693
1.0000000	0.5348297	0.0125344	3.5905461	1.0000000	Phosphate esters	1	13	245	1703
0.7095704	0.4963472	0.0116914	3.2899279	1.0000000	Dicarboxylic acids and derivatives	1	14	245	1702
0.5743186	0.4942833	0.0567131	1.9810519	1.0000000	Amines	2	28	244	1688
0.4982029	0.3851650	0.0092075	2.4611797	1.0000000	Halobenzenes	1	18	245	1698
0.4994651	0.3646829	0.0087418	2.3146946	1.0000000	Toluenes	1	19	245	1697
0.3472809	0.3144065	0.0075880	1.9629541	1.0000000	Fluorotelomer PFAA precursors	1	22	245	1694
0.3472809	0.3144065	0.0075880	1.9629541	1.0000000	Phthalate	1	22	245	1694
0.3497980	0.3005618	0.0072675	1.8680690	1.0000000	Fatty alcohols	1	23	245	1693
0.3550796	0.2878706	0.0069727	1.7817217	1.0000000	Benzene and substituted derivatives	1	24	245	1692
0.3550796	0.2878706	0.0069727	1.7817217	1.0000000	Ethers	1	24	245	1692
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	1,3,5-triazines	0	4	246	1712
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Alkaloid	0	3	246	1713
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Alkanes	0	4	246	1712
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Alkyl chlorides	0	3	246	1713
1.0000000	0.0000000	0.0000000	5.9389670	1.0000000	Alpha-halocarboxylic acids and derivatives	0	6	246	1710
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Androgen antagonist	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Anesthetic	0	3	246	1713
1.0000000	0.0000000	0.0000000	5.9389670	1.0000000	Anisoles	0	6	246	1710
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Anthracenes	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Anthraquinones	0	3	246	1713
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Antibiotic	0	4	246	1712
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Aromatase inhibitor	0	4	246	1712
0.6063620	0.0000000	0.0000000	4.8505601	1.0000000	Aromatic oil	0	7	246	1709
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Benzoic acid	0	3	246	1713
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Benzyloxycarbonyls	0	4	246	1712
0.6063620	0.0000000	0.0000000	4.8505601	1.0000000	Cannabinoid receptor antagonist	0	7	246	1709
1.0000000	0.0000000	0.0000000	5.9389670	1.0000000	Carbohydrates and carbohydrate conjugates	0	6	246	1710
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Chlorohydrins	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Cinnamaldehydes	0	3	246	1713
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Cinnamic acids and derivatives	0	4	246	1712
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Corticosteroid	0	4	246	1712
0.6063620	0.0000000	0.0000000	4.8505601	1.0000000	Coumarin	0	7	246	1709
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Depsides and depsidones	0	3	246	1713
0.3910531	0.0000000	0.0000000	2.2885318	1.0000000	Diphenylmethanes	0	13	246	1703
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	DNA synthesis inhibitor	0	3	246	1713
1.0000000	0.0000000	0.0000000	37.1917505	1.0000000	Dopamine receptor agonist	0	2	246	1714
0.6063620	0.0000000	0.0000000	4.8505601	1.0000000	Estrogen	0	7	246	1709
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Fatty alcohol esters	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Fibrate	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Fungicide Benzimidazole Cytoskeleton and motor protein inhibitor	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Fungicide Dicarboximide Signal Transduction	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Fungicide Phenylbenzamide Respiration	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Fungicide Polychloroaromatic Lipid Synthesis or Transport / Membrane Integrity or Function	0	3	246	1713
0.6065058	0.0000000	0.0000000	4.0945622	1.0000000	Gamma butyrolactones	0	8	246	1708
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Glycogen phosphorylase inhibitor	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Herbicide Cyclohexanedione oxime Acetyl CoA carboxylase inhibitor	0	3	246	1713
1.0000000	0.0000000	0.0000000	7.6317715	1.0000000	Herbicide Diphenyl ether Protoporphyrinogen Oxidase inhibitor	0	5	246	1711
1.0000000	0.0000000	0.0000000	5.9389670	1.0000000	Herbicide Imidazolinone Acetolactate synthase inhibitor	0	6	246	1710
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Herbicide Phenoxyacetic Auxin mimic	0	4	246	1712
1.0000000	0.0000000	0.0000000	7.6317715	1.0000000	Herbicide Phenylurea Inhbition of photosynthesis at PSll	0	5	246	1711
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Herbicide Pyridyloxycarboxylic acid Auxin mimic	0	4	246	1712
0.6065058	0.0000000	0.0000000	4.0945622	1.0000000	Herbicide Thiocarbamate Very Long-Chain Fatty Acid Synthesis inhibitor	0	8	246	1708
0.6065058	0.0000000	0.0000000	4.0945622	1.0000000	Herbicide Triazine Inhibition of photosynthesis at PSll	0	8	246	1708
0.3820874	0.0000000	0.0000000	2.5113465	1.0000000	Imidazolidines	0	12	246	1704
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Insecticide Benzoylurea Chitin biosynthesis inhibitor	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Insecticide Diacylhydrazine Ecdysone receptor agonist	0	3	246	1713
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Insecticide Nitroguanidine NACHR Competative Modulator	0	4	246	1712
1.0000000	0.0000000	0.0000000	7.6317715	1.0000000	Insecticide Phosphoramidate AChE Inhibitor	0	5	246	1711
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Kinase inhibitor	0	4	246	1712
1.0000000	0.0000000	0.0000000	37.1917505	1.0000000	Methoxybenzenes	0	2	246	1714
1.0000000	0.0000000	0.0000000	5.9389670	1.0000000	Methoxyphenols	0	6	246	1710
1.0000000	0.0000000	0.0000000	7.6317715	1.0000000	Morpholines	0	5	246	1711
0.6237717	0.0000000	0.0000000	3.1155696	1.0000000	Naphthalene sulfonic acids and derivatives	0	10	246	1706
0.3910531	0.0000000	0.0000000	2.2885318	1.0000000	Naphthalenes	0	13	246	1703
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Neurokinin receptor antagonist	0	4	246	1712
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Nitrophenols	0	3	246	1713
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Organic carbonic acids and derivatives	0	3	246	1713
0.6065058	0.0000000	0.0000000	4.0945622	1.0000000	Organic cyanides	0	8	246	1708
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Organic metalloid salts	0	4	246	1712
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Organic nitro compounds	0	3	246	1713
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Organic nitroso compounds	0	4	246	1712
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Organobromides	0	3	246	1713
0.6065058	0.0000000	0.0000000	4.0945622	1.0000000	Organometallic Sn	0	8	246	1708
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Organonitrogen compounds	0	4	246	1712
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Organosulfonic acids and derivatives	0	3	246	1713
0.6063620	0.0000000	0.0000000	4.8505601	1.0000000	Phenol ethers	0	7	246	1709
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Phenoxy compounds	0	3	246	1713
0.6063620	0.0000000	0.0000000	4.8505601	1.0000000	Phenoxyacetic acid derivatives	0	7	246	1709
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Phenylhydrazines	0	3	246	1713
1.0000000	0.0000000	0.0000000	7.6317715	1.0000000	Phosphodiesterase inhibitor	0	5	246	1711
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Phosphonic acid diesters	0	3	246	1713
0.6063620	0.0000000	0.0000000	4.8505601	1.0000000	Progestogen	0	7	246	1709
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Pyranones and derivatives	0	4	246	1712
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Pyrazoles	0	4	246	1712
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Pyridinecarboxylic acids and derivatives	0	4	246	1712
0.6065058	0.0000000	0.0000000	4.0945622	1.0000000	Sesquiterpenoids	0	8	246	1708
1.0000000	0.0000000	0.0000000	5.9389670	1.0000000	Silicon PFASs	0	6	246	1710
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Sodium channel inhibitor	0	3	246	1713
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Tetracarboxylic acids and derivatives	0	4	246	1712
1.0000000	0.0000000	0.0000000	10.5932345	1.0000000	Thioureas	0	4	246	1712
1.0000000	0.0000000	0.0000000	5.9389670	1.0000000	Triazinones	0	6	246	1710
0.6063620	0.0000000	0.0000000	4.8505601	1.0000000	Vitamin B	0	7	246	1709
1.0000000	0.0000000	0.0000000	16.9121965	1.0000000	Xylenes	0	3	246	1713

DIO2

For DIO2

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0000237	35.5383595	4.5380638	1591.5876342	0.0020731	Herbicide Chloroacetamide Very Long-Chain Fatty Acid Synthesis inhibitor	7	1	321	1633
0.0000187	20.3484965	4.0356747	197.1556111	0.0020731	Estrogen nonsteroidal	8	2	320	1632
0.0002609	11.8319707	2.6840144	71.2785633	0.0152194	Quaternary ammonium salts	7	3	321	1631
0.0006151	8.8705109	2.2398629	41.5664715	0.0269114	Bisphenol	7	4	321	1630
0.0046367	Inf	2.0658544	Inf	0.0901575	Cinnamaldehydes	3	0	325	1634
0.0046367	Inf	2.0658544	Inf	0.0901575	Fungicide Phthalimide Multi-site activity	3	0	325	1634
0.0046367	Inf	2.0658544	Inf	0.0901575	Fungicide Thiocarbamate Multi-site activity	3	0	325	1634
0.0046367	Inf	2.0658544	Inf	0.0901575	Retinoid	3	0	325	1634
0.0045821	8.4013791	1.6254644	54.3339076	0.0901575	Organometallic Sn	5	3	323	1631
0.0058732	0.0000000	0.0000000	0.6442248	0.1027815	Alcohols and polyols	0	30	328	1604
0.0145901	0.0000000	0.0000000	0.7851724	0.2321157	Ethers	0	25	328	1609
0.0166094	2.5411843	1.1009965	5.5324058	0.2422209	PFAAs	11	22	317	1612
0.0244546	4.1957891	1.0065655	16.6110128	0.3291963	Sulfuric acid esters	5	6	323	1628
0.0355920	7.5200279	0.8579640	90.4924956	0.4449004	Antibiotic polyketide	3	2	325	1632
0.0743575	10.0013972	0.5191722	589.0165789	0.5421898	Aryl chlorides	2	1	326	1633
0.0743575	10.0013972	0.5191722	589.0165789	0.5421898	Fungicide Imidazole Sterol Biosynthesis in Membranes	2	1	326	1633
0.0743575	10.0013972	0.5191722	589.0165789	0.5421898	Lineolic acids and derivatives	2	1	326	1633
0.0743575	10.0013972	0.5191722	589.0165789	0.5421898	Organometallic Hg	2	1	326	1633
0.0743575	10.0013972	0.5191722	589.0165789	0.5421898	Tryptase inhibitor	2	1	326	1633
0.0624905	5.0124666	0.6683670	37.5891629	0.5421898	Insecticide Organophosphate AChE Inhibitor	3	3	325	1631
0.0546515	1.7646789	0.9746905	3.0705207	0.5421898	Other aliphatics	19	55	309	1579
0.0737918	0.1754905	0.0042803	1.0693795	0.5421898	Carboxylic acid derivatives	1	28	327	1606
0.0474688	0.1693344	0.0041352	1.0289678	0.5421898	Amines	1	29	327	1605
0.0570147	0.0000000	0.0000000	1.1277798	0.5421898	Organosilicon compounds	0	18	328	1616
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Adrenergic beta agonist	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Benzofuranones	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Biphenyls and derivatives	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Cinnamic acids and derivatives	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Glyceryl	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Halopyridines	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	HMGCoA inhibitor	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Kinase inhibitor	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Neurokinin receptor antagonist	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	PPARg agonist	2	2	326	1632
0.1324759	5.0001685	0.3612311	69.3203126	0.5944431	Serotonin receptor antagonist	2	2	326	1632
0.0961341	3.7579305	0.5479218	22.3250931	0.5944431	Azobenzenes	3	4	325	1630
0.1256308	2.5077119	0.5492858	9.4272436	0.5944431	1-hydroxy-2-unsubstituted benzenoids	4	8	324	1626
0.1272028	2.1551243	0.6735971	6.0246234	0.5944431	Fatty acids and conjugates	6	14	322	1620
0.1150900	1.8708692	0.7997926	4.0368078	0.5944431	Unclassed	10	27	318	1607
0.1363603	0.3878256	0.0761295	1.2339593	0.5965764	Carbonyl compounds	3	38	325	1596
0.1571039	0.2241779	0.0054166	1.3969231	0.6705652	Phthalate	1	22	327	1612
0.1665823	2.2827619	0.6175169	7.1850906	0.6940931	Insecticide Pyrethroid Sodium channel modulator	5	11	323	1623
0.1970651	3.3325275	0.2773229	29.2144241	0.8020093	Insecticide Arylalkyl organothiophosphate AChE Inhibitor	2	3	326	1631
0.2258422	2.1444670	0.3559891	9.4564320	0.8946589	Polymer unclassified	3	7	325	1627
0.2300552	0.2746652	0.0065732	1.7518296	0.8946589	Halobenzenes	1	18	327	1616
0.2362145	0.0000000	0.0000000	1.7902528	0.8986423	Imidazolidines	0	12	328	1622
0.2643525	2.4984709	0.2251265	17.5144369	0.9441160	Antifungal paraben	2	4	326	1630
0.2643525	2.4984709	0.2251265	17.5144369	0.9441160	Naphthols and derivatives	2	4	326	1630
0.2553962	1.7717604	0.5675161	4.7552743	0.9441160	Fluorotelomer PFAA precursors	6	17	322	1617
0.2711131	2.0041341	0.4559759	7.0022720	0.9488959	Amino acids, peptides, and analogues	4	10	324	1624
0.2962998	1.8208781	0.4202392	6.1937736	0.9971629	Insecticide Aryl organothiophosphate AChE Inhibitor	4	11	324	1623
0.2921177	0.5330098	0.1370522	1.4986981	0.9971629	Benzoic acids and derivatives	4	37	324	1597
0.4225349	2.4938888	0.0421695	48.0257439	1.0000000	Anilides	1	2	327	1632
0.4225349	2.4938888	0.0421695	48.0257439	1.0000000	Anthracenes	1	2	327	1632
0.4225349	2.4938888	0.0421695	48.0257439	1.0000000	Benzenesulfonyl compounds	1	2	327	1632
0.4225349	2.4938888	0.0421695	48.0257439	1.0000000	Depsides and depsidones	1	2	327	1632
0.4225349	2.4938888	0.0421695	48.0257439	1.0000000	Fungicide Anilinopyrimidine Amino Acid and Protein Synthesis	1	2	327	1632
0.4225349	2.4938888	0.0421695	48.0257439	1.0000000	Phenanthrenes and derivatives	1	2	327	1632
0.4225349	2.4938888	0.0421695	48.0257439	1.0000000	Vinyl chlorides	1	2	327	1632
0.3316398	1.9979807	0.1894720	12.2686000	1.0000000	Antifungal	2	5	326	1629
0.6278200	1.6641098	0.1635553	9.3596311	1.0000000	Herbicide Dinitroaniline Microtubule assembly inhibitor	2	6	326	1628
0.6278200	1.6641098	0.1635553	9.3596311	1.0000000	Sesquiterpenoids	2	6	326	1628
0.5192213	1.6620789	0.0315745	20.7722908	1.0000000	Antibiotic	1	3	327	1631
0.5192213	1.6620789	0.0315745	20.7722908	1.0000000	FASA based PFAA precursors	1	3	327	1631
0.5192213	1.6620789	0.0315745	20.7722908	1.0000000	Herbicide N-Phenylimide Protoporphyrinogen Oxidase inhibitor	1	3	327	1631
0.5192213	1.6620789	0.0315745	20.7722908	1.0000000	Phenylmethylamines	1	3	327	1631
0.5192213	1.6620789	0.0315745	20.7722908	1.0000000	Triazoles	1	3	327	1631
0.6513669	1.4256511	0.1438593	7.5325946	1.0000000	Herbicide Aryloxyphenoxypropionic Acetyl CoA carboxylase inhibitor	2	7	326	1627
0.6513669	1.4256511	0.1438593	7.5325946	1.0000000	Insecticide Chlorinated cyclodiene GABA-gated chloride channel blocker	2	7	326	1627
1.0000000	1.2460267	0.0252281	12.6479020	1.0000000	Antiviral	1	4	327	1630
1.0000000	1.2460267	0.0252281	12.6479020	1.0000000	Insecticide Phosphoramidate AChE Inhibitor	1	4	327	1630
1.0000000	1.2460267	0.0252281	12.6479020	1.0000000	Pyrrolidones	1	4	327	1630
1.0000000	0.9963321	0.0210017	8.9466070	1.0000000	Androgen	1	5	327	1629
1.0000000	0.9963321	0.0210017	8.9466070	1.0000000	Benzothiazoles	1	5	327	1629
1.0000000	0.9963321	0.0210017	8.9466070	1.0000000	COX inhibitor	1	5	327	1629
1.0000000	0.9963321	0.0210017	8.9466070	1.0000000	Diphenylethers	1	5	327	1629
1.0000000	0.9963321	0.0210017	8.9466070	1.0000000	Isoindolines	1	5	327	1629
1.0000000	0.9963321	0.0210017	8.9466070	1.0000000	Methoxyphenols	1	5	327	1629
1.0000000	0.9482780	0.2350987	2.8366733	1.0000000	Benzene and substituted derivatives	4	21	324	1613
1.0000000	0.9213472	0.2749960	2.4519041	1.0000000	Monoterpenoids	5	27	323	1607
1.0000000	0.9052541	0.0970575	4.1765945	1.0000000	Naphthalenes	2	11	326	1623
1.0000000	0.8780650	0.1639140	3.0610979	1.0000000	Toluenes	3	17	325	1617
1.0000000	0.8298401	0.0179850	6.8747128	1.0000000	Aromatic oil	1	6	327	1628
1.0000000	0.8298401	0.0179850	6.8747128	1.0000000	Estrogen flavonoid	1	6	327	1628
1.0000000	0.8298401	0.0179850	6.8747128	1.0000000	Insecticide Organochlorine Sodium channel modulator	1	6	327	1628
1.0000000	0.8293182	0.0897367	3.7516562	1.0000000	Phosphate esters	2	12	326	1622
1.0000000	0.7650801	0.0834362	3.4039751	1.0000000	Dicarboxylic acids and derivatives	2	13	326	1621
1.0000000	0.7109025	0.0157271	5.5630154	1.0000000	Benzenesulfonic acids and derivatives	1	7	327	1627
1.0000000	0.7109025	0.0157271	5.5630154	1.0000000	Organic cyanides	1	7	327	1627
0.6392052	0.6833889	0.1733977	1.9651489	1.0000000	Phenylpropanes	4	29	324	1605
0.7535498	0.6622911	0.0731470	2.8692926	1.0000000	Nitrobenzenes	2	15	326	1619
1.0000000	0.6216904	0.0139689	4.6633706	1.0000000	Halophenols	1	8	327	1626
1.0000000	0.5522974	0.0125629	4.0092876	1.0000000	Naphthalene sulfonic acids and derivatives	1	9	327	1625
0.5584758	0.5216152	0.0586390	2.1790053	1.0000000	Fungicide Triazole Sterol Biosynthesis in Membranes	2	19	326	1615
0.7028505	0.4967791	0.0114128	3.5133956	1.0000000	Cresols	1	10	327	1624
0.7028505	0.4967791	0.0114128	3.5133956	1.0000000	Insecticide Aliphatic organothiophosphate AChE Inhibitor	1	10	327	1624
0.3500164	0.4774653	0.0928492	1.5447851	1.0000000	Fatty acid esters	3	31	325	1603
0.4086068	0.4496622	0.0510158	1.8440247	1.0000000	Fatty alcohols	2	22	326	1612
0.4142846	0.4298503	0.0488919	1.7537226	1.0000000	Pharmaceutical unknown MOA	2	23	326	1611
0.7076828	0.4134887	0.0096439	2.8125898	1.0000000	Diphenylmethanes	1	12	327	1622
0.7076828	0.4134887	0.0096439	2.8125898	1.0000000	Insecticide Carbamate AChE Inhibitor	1	12	327	1622
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	1,3,5-triazines	0	4	328	1630
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Alkaloid	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Alkanes	0	4	328	1630
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Alkyl chlorides	0	3	328	1631
0.5975106	0.0000000	0.0000000	4.2359085	1.0000000	Alpha-halocarboxylic acids and derivatives	0	6	328	1628
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Androgen antagonist	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Androgen nonsteroidal antagonist	0	4	328	1630
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Anesthetic	0	3	328	1631
0.5975106	0.0000000	0.0000000	4.2359085	1.0000000	Anisoles	0	6	328	1628
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Anthraquinones	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Aromatase inhibitor	0	4	328	1630
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Benzenediols	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Benzoic acid	0	3	328	1631
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	Benzophenones	0	7	328	1627
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Benzyloxycarbonyls	0	4	328	1630
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	Cannabinoid receptor antagonist	0	7	328	1627
0.5975106	0.0000000	0.0000000	4.2359085	1.0000000	Carbohydrates and carbohydrate conjugates	0	6	328	1628
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Chlorohydrins	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Corticosteroid	0	4	328	1630
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	Coumarin	0	7	328	1627
0.5975106	0.0000000	0.0000000	4.2359085	1.0000000	Cumenes	0	6	328	1628
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	DNA synthesis inhibitor	0	3	328	1631
1.0000000	0.0000000	0.0000000	26.5592830	1.0000000	Dopamine receptor agonist	0	2	328	1632
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	Estrogen	0	7	328	1627
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Fatty alcohol esters	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Fibrate	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Fungicide Benzimidazole Cytoskeleton and motor protein inhibitor	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Fungicide Dicarboximide Signal Transduction	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Fungicide Phenylbenzamide Respiration	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Fungicide Polychloroaromatic Lipid Synthesis or Transport / Membrane Integrity or Function	0	3	328	1631
0.3661738	0.0000000	0.0000000	2.9196968	1.0000000	Gamma butyrolactones	0	8	328	1626
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Glycogen phosphorylase inhibitor	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Herbicide Cyclohexanedione oxime Acetyl CoA carboxylase inhibitor	0	3	328	1631
0.5973048	0.0000000	0.0000000	5.4439403	1.0000000	Herbicide Diphenyl ether Protoporphyrinogen Oxidase inhibitor	0	5	328	1629
0.5975106	0.0000000	0.0000000	4.2359085	1.0000000	Herbicide Imidazolinone Acetolactate synthase inhibitor	0	6	328	1628
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Herbicide Phenoxyacetic Auxin mimic	0	4	328	1630
0.5973048	0.0000000	0.0000000	5.4439403	1.0000000	Herbicide Phenylurea Inhbition of photosynthesis at PSll	0	5	328	1629
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Herbicide Pyridyloxycarboxylic acid Auxin mimic	0	4	328	1630
0.3661738	0.0000000	0.0000000	2.9196968	1.0000000	Herbicide Thiocarbamate Very Long-Chain Fatty Acid Synthesis inhibitor	0	8	328	1626
0.3661738	0.0000000	0.0000000	2.9196968	1.0000000	Herbicide Triazine Inhibition of photosynthesis at PSll	0	8	328	1626
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Herbicide Triazolopyrimidine Acetolactate synthase inhibitor	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Insecticide Benzoylurea Chitin biosynthesis inhibitor	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Insecticide Diacylhydrazine Ecdysone receptor agonist	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Insecticide Nitroguanidine NACHR Competative Modulator	0	4	328	1630
1.0000000	0.0000000	0.0000000	26.5592830	1.0000000	Methoxybenzenes	0	2	328	1632
0.5973048	0.0000000	0.0000000	5.4439403	1.0000000	Morpholines	0	5	328	1629
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Nitrophenols	0	3	328	1631
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Organic carbonic acids and derivatives	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Organic metalloid salts	0	4	328	1630
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Organic nitro compounds	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Organic nitroso compounds	0	4	328	1630
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Organobromides	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Organonitrogen compounds	0	4	328	1630
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Organosulfonic acids and derivatives	0	3	328	1631
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	PFAA precursors	0	7	328	1627
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	Phenol ethers	0	7	328	1627
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Phenoxy compounds	0	3	328	1631
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	Phenoxyacetic acid derivatives	0	7	328	1627
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Phenylhydrazines	0	3	328	1631
0.5973048	0.0000000	0.0000000	5.4439403	1.0000000	Phosphodiesterase inhibitor	0	5	328	1629
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Phosphonic acid diesters	0	3	328	1631
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	Progestogen	0	7	328	1627
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Pyranones and derivatives	0	4	328	1630
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Pyrazoles	0	4	328	1630
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Pyridinecarboxylic acids and derivatives	0	4	328	1630
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Side-chain aromatics	0	4	328	1630
0.5975106	0.0000000	0.0000000	4.2359085	1.0000000	Silicon PFASs	0	6	328	1628
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Sodium channel inhibitor	0	3	328	1631
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Tetracarboxylic acids and derivatives	0	4	328	1630
1.0000000	0.0000000	0.0000000	7.5578204	1.0000000	Thioureas	0	4	328	1630
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Thyroid hormone	0	3	328	1631
0.5975106	0.0000000	0.0000000	4.2359085	1.0000000	Triazinones	0	6	328	1628
0.6089309	0.0000000	0.0000000	3.4592427	1.0000000	Vitamin B	0	7	328	1627
1.0000000	0.0000000	0.0000000	12.0731320	1.0000000	Xylenes	0	3	328	1631

DIO3

For DIO3

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0000258	35.0155107	4.4714250	1568.3849512	0.0022538	Herbicide Chloroacetamide Very Long-Chain Fatty Acid Synthesis inhibitor	7	1	325	1629
0.0000258	35.0155107	4.4714250	1568.3849512	0.0022538	Herbicide Triazine Inhibition of photosynthesis at PSll	7	1	325	1629
0.0002825	11.6580174	2.6443576	70.1918987	0.0164770	Quaternary ammonium salts	7	3	325	1627
0.0006646	8.7402222	2.2071299	40.9936493	0.0290752	Bisphenol	7	4	325	1626
0.0048089	Inf	2.0358336	Inf	0.0935067	Cinnamaldehydes	3	0	329	1630
0.0048089	Inf	2.0358336	Inf	0.0935067	Fungicide Phthalimide Multi-site activity	3	0	329	1630
0.0048089	Inf	2.0358336	Inf	0.0935067	Fungicide Thiocarbamate Multi-site activity	3	0	329	1630
0.0048089	Inf	2.0358336	Inf	0.0935067	Retinoid	3	0	329	1630
0.0034970	19.8172136	1.9532697	973.2823962	0.0935067	Antibiotic polyketide	4	1	328	1629
0.0058108	0.0000000	0.0000000	0.6348346	0.1016884	Alcohols and polyols	0	30	332	1600
0.0144268	0.0000000	0.0000000	0.7737403	0.2295177	Ethers	0	25	332	1605
0.0162228	4.9635409	1.1353425	21.6981396	0.2365830	Estrogen nonsteroidal	5	5	327	1625
0.0319772	4.9514576	0.9173501	26.7263933	0.4304621	Sesquiterpenoids	4	4	328	1626
0.0364053	0.0000000	0.0000000	0.9367034	0.4550663	Fungicide Triazole Sterol Biosynthesis in Membranes	0	21	332	1609
0.0500416	3.9594490	0.7813475	18.4967236	0.5473302	Insecticide Chlorinated cyclodiene GABA-gated chloride channel blocker	4	5	328	1625
0.0473808	0.1729384	0.0042183	1.0537561	0.5473302	Carboxylic acid derivatives	1	28	331	1602
0.0567660	0.0000000	0.0000000	1.1113794	0.5843561	Organosilicon compounds	0	18	332	1612
0.0760683	9.8548166	0.5116482	580.4900579	0.6050890	Aryl chlorides	2	1	330	1629
0.0760683	9.8548166	0.5116482	580.4900579	0.6050890	Depsides and depsidones	2	1	330	1629
0.0760683	9.8548166	0.5116482	580.4900579	0.6050890	Lineolic acids and derivatives	2	1	330	1629
0.0760683	9.8548166	0.5116482	580.4900579	0.6050890	Tryptase inhibitor	2	1	330	1629
0.0644797	4.9394480	0.6586628	37.0397871	0.6050890	Naphthols and derivatives	3	3	329	1627
0.0990325	3.7031904	0.5399719	21.9987249	0.6956864	Azobenzenes	3	4	329	1626
0.0990325	3.7031904	0.5399719	21.9987249	0.6956864	Progestogen	3	4	329	1626
0.0993838	2.8253810	0.6030306	11.1867656	0.6956864	Sulfuric acid esters	4	7	328	1623
0.1353239	4.9275114	0.3559961	68.3007202	0.7400524	Benzofuranones	2	2	330	1628
0.1353239	4.9275114	0.3559961	68.3007202	0.7400524	Cinnamic acids and derivatives	2	2	330	1628
0.1353239	4.9275114	0.3559961	68.3007202	0.7400524	Glyceryl	2	2	330	1628
0.1353239	4.9275114	0.3559961	68.3007202	0.7400524	HMGCoA inhibitor	2	2	330	1628
0.1353239	4.9275114	0.3559961	68.3007202	0.7400524	PPARg agonist	2	2	330	1628
0.1300344	2.4710014	0.5413081	9.2872667	0.7400524	1-hydroxy-2-unsubstituted benzenoids	4	8	328	1622
0.1308264	2.1234595	0.6637476	5.9355552	0.7400524	Fatty acids and conjugates	6	14	326	1616
0.1551174	2.4755285	0.6594501	8.0120251	0.7882308	Insecticide Aryl organothiophosphate AChE Inhibitor	5	10	327	1620
0.1576462	0.2209199	0.0053382	1.3765264	0.7882308	Fluorotelomer PFAA precursors	1	22	331	1608
0.1576462	0.2209199	0.0053382	1.3765264	0.7882308	Phthalate	1	22	331	1608
0.2010154	3.2841103	0.2733031	28.7903202	0.9507485	Antiviral	2	3	330	1627
0.2010154	3.2841103	0.2733031	28.7903202	0.9507485	Insecticide Arylalkyl organothiophosphate AChE Inhibitor	2	3	330	1627
0.2148047	0.3468821	0.0398537	1.3870130	0.9815311	Amines	2	28	330	1602
0.2290132	0.2706752	0.0064780	1.7262255	0.9815311	Halobenzenes	1	18	331	1612
0.2299587	0.2562727	0.0061503	1.6233819	0.9815311	Toluenes	1	19	331	1611
0.2287691	0.0000000	0.0000000	1.9542532	0.9815311	Insecticide Aliphatic organothiophosphate AChE Inhibitor	0	11	332	1619
0.3098681	4.9156473	0.0625087	385.2996888	1.0000000	Dopamine receptor agonist	1	1	331	1629
0.2692832	2.4620095	0.2218629	17.2591161	1.0000000	Antifungal paraben	2	4	330	1626
0.2692832	2.4620095	0.2218629	17.2591161	1.0000000	Benzothiazoles	2	4	330	1626
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Androgen antagonist	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Anthracenes	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Benzenesulfonyl compounds	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Fungicide Anilinopyrimidine Amino Acid and Protein Synthesis	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Fungicide Imidazole Sterol Biosynthesis in Membranes	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Fungicide Polychloroaromatic Lipid Synthesis or Transport / Membrane Integrity or Function	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Insecticide Diacylhydrazine Ecdysone receptor agonist	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Organometallic Hg	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Phenanthrenes and derivatives	1	2	331	1628
0.4267680	2.4579132	0.0415593	47.3301553	1.0000000	Vinyl chlorides	1	2	331	1628
0.3874748	2.1132214	0.3508188	9.3176960	1.0000000	Polymer unclassified	3	7	329	1623
0.3373835	1.9689582	0.1867245	12.0896167	1.0000000	Antifungal	2	5	330	1625
0.3373835	1.9689582	0.1867245	12.0896167	1.0000000	Insecticide Organochlorine Sodium channel modulator	2	5	330	1625
0.2760943	1.6477678	0.5312792	4.3752910	1.0000000	Fatty alcohols	6	18	326	1612
0.3309791	1.6438180	0.3840076	5.4677325	1.0000000	Insecticide Pyrethroid Sodium channel modulator	4	12	328	1618
0.6297011	1.6399161	0.1611829	9.2229863	1.0000000	Herbicide Dinitroaniline Microtubule assembly inhibitor	2	6	330	1624
0.6297011	1.6399161	0.1611829	9.2229863	1.0000000	Organic cyanides	2	6	330	1624
0.6297011	1.6399161	0.1611829	9.2229863	1.0000000	Organometallic Sn	2	6	330	1624
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	1,3,5-triazines	1	3	331	1627
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	Adrenergic beta agonist	1	3	331	1627
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	Biphenyls and derivatives	1	3	331	1627
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	Corticosteroid	1	3	331	1627
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	FASA based PFAA precursors	1	3	331	1627
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	Halopyridines	1	3	331	1627
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	Herbicide N-Phenylimide Protoporphyrinogen Oxidase inhibitor	1	3	331	1627
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	Phenylmethylamines	1	3	331	1627
0.5239161	1.6379828	0.0311175	20.4703761	1.0000000	Triazoles	1	3	331	1627
0.2645102	1.5937665	0.6551882	3.5151271	1.0000000	Unclassed	9	28	323	1602
0.6539818	1.4049214	0.1417719	7.4226195	1.0000000	Herbicide Aryloxyphenoxypropionic Acetyl CoA carboxylase inhibitor	2	7	330	1623
0.2694406	1.3720820	0.7263732	2.4575543	1.0000000	Other aliphatics	16	58	316	1572
1.0000000	1.2279349	0.0248630	12.4639272	1.0000000	Pyrrolidones	1	4	331	1626
0.8113715	1.1354020	0.3790991	2.8499821	1.0000000	Monoterpenoids	6	26	326	1604
0.8153542	1.0926772	0.3659431	2.7300996	1.0000000	PFAAs	6	27	326	1603
1.0000000	1.0525211	0.1928642	3.8009334	1.0000000	Nitrobenzenes	3	14	329	1616
1.0000000	0.9818806	0.0206977	8.8166350	1.0000000	Androgen	1	5	331	1625
1.0000000	0.9818806	0.0206977	8.8166350	1.0000000	COX inhibitor	1	5	331	1625
1.0000000	0.9818806	0.0206977	8.8166350	1.0000000	Diphenylethers	1	5	331	1625
1.0000000	0.9818806	0.0206977	8.8166350	1.0000000	Insecticide Organophosphate AChE Inhibitor	1	5	331	1625
1.0000000	0.9818806	0.0206977	8.8166350	1.0000000	Isoindolines	1	5	331	1625
1.0000000	0.9818806	0.0206977	8.8166350	1.0000000	Methoxyphenols	1	5	331	1625
1.0000000	0.9343892	0.2316724	2.7949409	1.0000000	Pharmaceutical unknown MOA	4	21	328	1609
1.0000000	0.8920718	0.0956496	4.1153437	1.0000000	Naphthalenes	2	11	330	1619
1.0000000	0.8748936	0.2617981	2.3182786	1.0000000	Phenylpropanes	5	28	327	1602
1.0000000	0.8442117	0.2532558	2.2282595	1.0000000	Fatty acid esters	5	29	327	1601
0.8347532	0.8388096	0.2860208	2.0376895	1.0000000	Carbonyl compounds	6	35	326	1595
1.0000000	0.8178031	0.0177246	6.7746515	1.0000000	Estrogen flavonoid	1	6	331	1624
1.0000000	0.8178031	0.0177246	6.7746515	1.0000000	PFAA precursors	1	6	331	1624
1.0000000	0.8178031	0.0177246	6.7746515	1.0000000	Vitamin B	1	6	331	1624
1.0000000	0.7539463	0.0822256	3.3542090	1.0000000	Dicarboxylic acids and derivatives	2	13	330	1617
0.7873198	0.6666056	0.1270060	2.2381044	1.0000000	Benzene and substituted derivatives	3	22	329	1608
1.0000000	0.5442831	0.0123810	3.9508824	1.0000000	Naphthalene sulfonic acids and derivatives	1	9	331	1621
0.2922433	0.5251940	0.1350515	1.4765759	1.0000000	Benzoic acids and derivatives	4	37	328	1593
0.7022061	0.4895696	0.0112475	3.4621846	1.0000000	Cresols	1	10	331	1620
0.7030913	0.4447943	0.0103032	3.0791593	1.0000000	Imidazolidines	1	11	331	1619
0.7084897	0.4074861	0.0095042	2.7715913	1.0000000	Diphenylmethanes	1	12	331	1618
0.7084897	0.4074861	0.0095042	2.7715913	1.0000000	Insecticide Carbamate AChE Inhibitor	1	12	331	1618
0.4871522	0.3759164	0.0088196	2.5190497	1.0000000	Amino acids, peptides, and analogues	1	13	331	1617
0.4871522	0.3759164	0.0088196	2.5190497	1.0000000	Phosphate esters	1	13	331	1617
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Alkaloid	0	3	332	1627
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Alkanes	0	4	332	1626
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Alkyl chlorides	0	3	332	1627
0.5975704	0.0000000	0.0000000	4.1744226	1.0000000	Alpha-halocarboxylic acids and derivatives	0	6	332	1624
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Androgen nonsteroidal antagonist	0	4	332	1626
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Anesthetic	0	3	332	1627
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Anilides	0	3	332	1627
0.5975704	0.0000000	0.0000000	4.1744226	1.0000000	Anisoles	0	6	332	1624
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Anthraquinones	0	3	332	1627
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Antibiotic	0	4	332	1626
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Aromatase inhibitor	0	4	332	1626
0.6099492	0.0000000	0.0000000	3.4090189	1.0000000	Aromatic oil	0	7	332	1623
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Benzenediols	0	3	332	1627
0.3655439	0.0000000	0.0000000	2.8773076	1.0000000	Benzenesulfonic acids and derivatives	0	8	332	1622
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Benzoic acid	0	3	332	1627
0.6099492	0.0000000	0.0000000	3.4090189	1.0000000	Benzophenones	0	7	332	1623
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Benzyloxycarbonyls	0	4	332	1626
0.6099492	0.0000000	0.0000000	3.4090189	1.0000000	Cannabinoid receptor antagonist	0	7	332	1623
0.5975704	0.0000000	0.0000000	4.1744226	1.0000000	Carbohydrates and carbohydrate conjugates	0	6	332	1624
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Chlorohydrins	0	3	332	1627
0.6099492	0.0000000	0.0000000	3.4090189	1.0000000	Coumarin	0	7	332	1623
0.5975704	0.0000000	0.0000000	4.1744226	1.0000000	Cumenes	0	6	332	1624
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	DNA synthesis inhibitor	0	3	332	1627
0.6099492	0.0000000	0.0000000	3.4090189	1.0000000	Estrogen	0	7	332	1623
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Fatty alcohol esters	0	3	332	1627
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Fibrate	0	3	332	1627
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Fungicide Benzimidazole Cytoskeleton and motor protein inhibitor	0	3	332	1627
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Fungicide Dicarboximide Signal Transduction	0	3	332	1627
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Fungicide Phenylbenzamide Respiration	0	3	332	1627
0.3655439	0.0000000	0.0000000	2.8773076	1.0000000	Gamma butyrolactones	0	8	332	1622
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Glycogen phosphorylase inhibitor	0	3	332	1627
0.3717095	0.0000000	0.0000000	2.4872779	1.0000000	Halophenols	0	9	332	1621
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Herbicide Cyclohexanedione oxime Acetyl CoA carboxylase inhibitor	0	3	332	1627
0.5963742	0.0000000	0.0000000	5.3649519	1.0000000	Herbicide Diphenyl ether Protoporphyrinogen Oxidase inhibitor	0	5	332	1625
0.5975704	0.0000000	0.0000000	4.1744226	1.0000000	Herbicide Imidazolinone Acetolactate synthase inhibitor	0	6	332	1624
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Herbicide Phenoxyacetic Auxin mimic	0	4	332	1626
0.5963742	0.0000000	0.0000000	5.3649519	1.0000000	Herbicide Phenylurea Inhbition of photosynthesis at PSll	0	5	332	1625
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Herbicide Pyridyloxycarboxylic acid Auxin mimic	0	4	332	1626
0.3655439	0.0000000	0.0000000	2.8773076	1.0000000	Herbicide Thiocarbamate Very Long-Chain Fatty Acid Synthesis inhibitor	0	8	332	1622
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Herbicide Triazolopyrimidine Acetolactate synthase inhibitor	0	3	332	1627
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Insecticide Benzoylurea Chitin biosynthesis inhibitor	0	3	332	1627
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Insecticide Nitroguanidine NACHR Competative Modulator	0	4	332	1626
0.5963742	0.0000000	0.0000000	5.3649519	1.0000000	Insecticide Phosphoramidate AChE Inhibitor	0	5	332	1625
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Kinase inhibitor	0	4	332	1626
1.0000000	0.0000000	0.0000000	26.1790929	1.0000000	Methoxybenzenes	0	2	332	1628
0.5963742	0.0000000	0.0000000	5.3649519	1.0000000	Morpholines	0	5	332	1625
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Neurokinin receptor antagonist	0	4	332	1626
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Nitrophenols	0	3	332	1627
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Organic carbonic acids and derivatives	0	3	332	1627
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Organic metalloid salts	0	4	332	1626
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Organic nitro compounds	0	3	332	1627
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Organic nitroso compounds	0	4	332	1626
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Organobromides	0	3	332	1627
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Organonitrogen compounds	0	4	332	1626
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Organosulfonic acids and derivatives	0	3	332	1627
0.6099492	0.0000000	0.0000000	3.4090189	1.0000000	Phenol ethers	0	7	332	1623
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Phenoxy compounds	0	3	332	1627
0.6099492	0.0000000	0.0000000	3.4090189	1.0000000	Phenoxyacetic acid derivatives	0	7	332	1623
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Phenylhydrazines	0	3	332	1627
0.5963742	0.0000000	0.0000000	5.3649519	1.0000000	Phosphodiesterase inhibitor	0	5	332	1625
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Phosphonic acid diesters	0	3	332	1627
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Pyranones and derivatives	0	4	332	1626
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Pyrazoles	0	4	332	1626
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Pyridinecarboxylic acids and derivatives	0	4	332	1626
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Serotonin receptor antagonist	0	4	332	1626
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Side-chain aromatics	0	4	332	1626
0.5975704	0.0000000	0.0000000	4.1744226	1.0000000	Silicon PFASs	0	6	332	1624
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Sodium channel inhibitor	0	3	332	1627
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Tetracarboxylic acids and derivatives	0	4	332	1626
1.0000000	0.0000000	0.0000000	7.4482099	1.0000000	Thioureas	0	4	332	1626
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Thyroid hormone	0	3	332	1627
0.5975704	0.0000000	0.0000000	4.1744226	1.0000000	Triazinones	0	6	332	1624
1.0000000	0.0000000	0.0000000	11.8982067	1.0000000	Xylenes	0	3	332	1627

IYD

For IYD

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0000061	28.4636401	5.3730297	280.6420376	0.0010623	Insecticide Chlorinated cyclodiene GABA-gated chloride channel blocker	7	2	214	1746
0.0000234	5.3920218	2.4265620	11.5894098	0.0020485	PFAAs	13	20	208	1728
0.0001176	16.1859485	3.4275574	100.8398210	0.0068621	Quaternary ammonium salts	6	3	215	1745
0.0005319	9.7038914	2.4453693	40.5850137	0.0232707	Bisphenol	6	5	215	1743
0.0009648	8.0855389	2.1411398	30.5397578	0.0337694	1-hydroxy-2-unsubstituted benzenoids	6	6	215	1742
0.0025810	6.0609404	1.7157668	20.1290472	0.0752799	Sulfuric acid esters	6	8	215	1740
0.0075059	8.0204083	1.4828070	43.4152724	0.1641923	Azobenzenes	4	4	217	1744
0.0075059	8.0204083	1.4828070	43.4152724	0.1641923	Sesquiterpenoids	4	4	217	1744
0.0102784	5.0277195	1.2822072	17.6105803	0.1998587	Polymer unclassified	5	8	216	1740
0.0187767	5.3438713	1.1003303	22.7362664	0.3285916	Estrogen nonsteroidal	4	6	217	1742
0.0348474	15.9091055	0.8250675	935.4537166	0.5081920	Cinnamaldehydes	2	1	219	1747
0.0346557	5.9902639	0.8717473	35.6454134	0.5081920	Insecticide Organochlorine Sodium channel modulator	3	4	218	1744
0.0417969	0.0000000	0.0000000	1.0265154	0.5567561	Alcohols and polyols	0	30	221	1718
0.0445405	0.0000000	0.0000000	0.9263046	0.5567561	Monoterpenoids	0	33	221	1715
0.0509455	4.7909087	0.7389016	24.8072011	0.5943643	Naphthalene sulfonic acids and derivatives	3	5	218	1743
0.0645718	7.9564482	0.5740981	110.3150852	0.6364787	Glyceryl	2	2	219	1746
0.0596881	2.2251187	0.8675092	5.0701325	0.6364787	Unclassed	8	29	213	1719
0.0654664	0.0000000	0.0000000	1.1059679	0.6364787	Carboxylic acid derivatives	0	28	221	1720
0.0707826	2.4516147	0.8777795	5.9917977	0.6519450	Phenylpropanes	7	23	214	1725
0.0997871	5.3042310	0.4407893	46.5445100	0.8392775	Phenylmethylamines	2	3	219	1745
0.1007133	0.0000000	0.0000000	1.3077434	0.8392775	Fatty alcohols	0	24	221	1724
0.1388979	3.9767803	0.3578251	27.9474267	1.0000000	Anilides	2	4	219	1744
0.1388979	3.9767803	0.3578251	27.9474267	1.0000000	Naphthols and derivatives	2	4	219	1744
0.3004747	3.9632725	0.0669590	76.3259080	1.0000000	Aryl chlorides	1	2	220	1746
0.3004747	3.9632725	0.0669590	76.3259080	1.0000000	Benzenediols	1	2	220	1746
0.3004747	3.9632725	0.0669590	76.3259080	1.0000000	Fungicide Anilinopyrimidine Amino Acid and Protein Synthesis	1	2	220	1746
0.3004747	3.9632725	0.0669590	76.3259080	1.0000000	Herbicide Triazolopyrimidine Acetolactate synthase inhibitor	1	2	220	1746
0.3004747	3.9632725	0.0669590	76.3259080	1.0000000	Lineolic acids and derivatives	1	2	220	1746
0.3004747	3.9632725	0.0669590	76.3259080	1.0000000	PPARg agonist	1	2	220	1746
0.3004747	3.9632725	0.0669590	76.3259080	1.0000000	Tryptase inhibitor	1	2	220	1746
0.1805948	3.1805974	0.3011743	19.5686809	1.0000000	Antifungal	2	5	219	1743
0.3791091	2.6420791	0.0501378	33.0632249	1.0000000	Antibiotic polyketide	1	3	220	1745
0.3791091	2.6420791	0.0501378	33.0632249	1.0000000	Benzofuranones	1	3	220	1745
0.3791091	2.6420791	0.0501378	33.0632249	1.0000000	FASA based PFAA precursors	1	3	220	1745
0.3791091	2.6420791	0.0501378	33.0632249	1.0000000	Herbicide Pyridyloxycarboxylic acid Auxin mimic	1	3	220	1745
0.3791091	2.6420791	0.0501378	33.0632249	1.0000000	Side-chain aromatics	1	3	220	1745
0.3791091	2.6420791	0.0501378	33.0632249	1.0000000	Thyroid hormone	1	3	220	1745
0.3791091	2.6420791	0.0501378	33.0632249	1.0000000	Triazoles	1	3	220	1745
0.1718190	2.3902627	0.4195380	9.3778417	1.0000000	Naphthalenes	3	10	218	1738
0.4489395	1.9809820	0.0400620	20.1342836	1.0000000	Antiviral	1	4	220	1744
0.4489395	1.9809820	0.0400620	20.1342836	1.0000000	Morpholines	1	4	220	1744
0.4489395	1.9809820	0.0400620	20.1342836	1.0000000	Pyrrolidones	1	4	220	1744
0.2840047	1.8760945	0.4551300	5.8234968	1.0000000	Fatty acids and conjugates	4	17	217	1731
0.4118864	1.8358975	0.3329889	6.7545411	1.0000000	Insecticide Pyrethroid Sodium channel modulator	3	13	218	1735
0.2139879	1.6484734	0.6090564	3.8393161	1.0000000	Benzoic acids and derivatives	7	34	214	1714
0.5109479	1.5840927	0.0333518	14.2494246	1.0000000	Antifungal paraben	1	5	220	1743
0.5109479	1.5840927	0.0333518	14.2494246	1.0000000	Biphenyls and derivatives	1	5	220	1743
0.5109479	1.5840927	0.0333518	14.2494246	1.0000000	COX inhibitor	1	5	220	1743
0.5109479	1.5840927	0.0333518	14.2494246	1.0000000	Diphenylethers	1	5	220	1743
0.5109479	1.5840927	0.0333518	14.2494246	1.0000000	Isoindolines	1	5	220	1743
0.6496959	1.4417776	0.1542835	6.6704393	1.0000000	Diphenylmethanes	2	11	219	1737
0.6651805	1.3209460	0.1427034	5.9927675	1.0000000	Phosphate esters	2	12	219	1736
0.5660067	1.3194872	0.0285623	10.9533896	1.0000000	Estrogen flavonoid	1	6	220	1742
0.5660067	1.3194872	0.0285623	10.9533896	1.0000000	PFAA precursors	1	6	220	1742
0.5660067	1.3194872	0.0285623	10.9533896	1.0000000	Vitamin B	1	6	220	1742
0.7298503	1.2521370	0.2354111	4.3049489	1.0000000	Fungicide Triazole Sterol Biosynthesis in Membranes	3	19	218	1729
0.7374023	1.1888780	0.2244168	4.0573834	1.0000000	Fluorotelomer PFAA precursors	3	20	218	1728
0.6986439	1.1310206	0.1239391	4.9755315	1.0000000	Amino acids, peptides, and analogues	2	14	219	1734
0.6986439	1.1310206	0.1239391	4.9755315	1.0000000	Nitrobenzenes	2	14	219	1734
1.0000000	1.1304257	0.0249720	8.8658943	1.0000000	Benzenesulfonic acids and derivatives	1	7	220	1741
1.0000000	1.1304257	0.0249720	8.8658943	1.0000000	Halophenols	1	7	220	1741
1.0000000	1.1304257	0.0249720	8.8658943	1.0000000	Herbicide Dinitroaniline Microtubule assembly inhibitor	1	7	220	1741
0.4577359	0.6895810	0.2415890	1.6068370	1.0000000	Other aliphatics	6	68	215	1680
1.0000000	0.6850458	0.0777646	2.8039401	1.0000000	Pharmaceutical unknown MOA	2	23	219	1725
0.6150608	0.6364988	0.1245129	2.0368436	1.0000000	Carbonyl compounds	3	37	218	1711
0.5744311	0.5059543	0.0582790	2.0121565	1.0000000	Fatty acid esters	2	31	219	1717
0.7114512	0.4921811	0.0116842	3.1986101	1.0000000	Organosilicon compounds	1	16	220	1732
0.7140528	0.4370024	0.0104417	2.7948065	1.0000000	Toluenes	1	18	220	1730
0.5044381	0.3567378	0.0086054	2.2292737	1.0000000	Phthalate	1	22	220	1726
0.5093499	0.3410331	0.0082421	2.1215249	1.0000000	Benzene and substituted derivatives	1	23	220	1725
0.3506156	0.3266368	0.0079078	2.0234526	1.0000000	Ethers	1	24	220	1724
0.3584997	0.2898452	0.0070483	1.7768471	1.0000000	Amines	1	27	220	1721
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	1,3,5-triazines	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Adrenergic beta agonist	0	4	221	1744
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Alkaloid	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Alkanes	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Alkyl chlorides	0	3	221	1745
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Alpha-halocarboxylic acids and derivatives	0	7	221	1741
1.0000000	0.0000000	0.0000000	6.7380194	1.0000000	Androgen	0	6	221	1742
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Androgen antagonist	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Androgen nonsteroidal antagonist	0	4	221	1744
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Anesthetic	0	3	221	1745
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Anisoles	0	5	221	1743
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Anthracenes	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Anthraquinones	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Antibiotic	0	4	221	1744
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Aromatase inhibitor	0	4	221	1744
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Aromatic oil	0	7	221	1741
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Benzenesulfonyl compounds	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Benzoic acid	0	3	221	1745
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Benzophenones	0	7	221	1741
1.0000000	0.0000000	0.0000000	6.7380194	1.0000000	Benzothiazoles	0	6	221	1742
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Benzyloxycarbonyls	0	4	221	1744
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Cannabinoid receptor antagonist	0	7	221	1741
1.0000000	0.0000000	0.0000000	6.7380194	1.0000000	Carbohydrates and carbohydrate conjugates	0	6	221	1742
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Chlorohydrins	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Cinnamic acids and derivatives	0	4	221	1744
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Corticosteroid	0	4	221	1744
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Coumarin	0	7	221	1741
0.6237743	0.0000000	0.0000000	3.1560268	1.0000000	Cresols	0	11	221	1737
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Cumenes	0	5	221	1743
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Depsides and depsidones	0	3	221	1745
0.3990497	0.0000000	0.0000000	2.2046417	1.0000000	Dicarboxylic acids and derivatives	0	15	221	1733
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	DNA synthesis inhibitor	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Dopamine receptor agonist	0	3	221	1745
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Estrogen	0	7	221	1741
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Fatty alcohol esters	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Fibrate	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Fungicide Benzimidazole Cytoskeleton and motor protein inhibitor	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Fungicide Dicarboximide Signal Transduction	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Fungicide Imidazole Sterol Biosynthesis in Membranes	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Fungicide Phenylbenzamide Respiration	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Fungicide Phthalimide Multi-site activity	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Fungicide Polychloroaromatic Lipid Synthesis or Transport / Membrane Integrity or Function	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Fungicide Thiocarbamate Multi-site activity	0	4	221	1744
0.6089194	0.0000000	0.0000000	4.6456988	1.0000000	Gamma butyrolactones	0	8	221	1740
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Glycogen phosphorylase inhibitor	0	3	221	1745
0.2506343	0.0000000	0.0000000	1.7959844	1.0000000	Halobenzenes	0	18	221	1730
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Halopyridines	0	4	221	1744
0.6093931	0.0000000	0.0000000	4.0164868	1.0000000	Herbicide Aryloxyphenoxypropionic Acetyl CoA carboxylase inhibitor	0	9	221	1739
0.6089194	0.0000000	0.0000000	4.6456988	1.0000000	Herbicide Chloroacetamide Very Long-Chain Fatty Acid Synthesis inhibitor	0	8	221	1740
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Herbicide Cyclohexanedione oxime Acetyl CoA carboxylase inhibitor	0	3	221	1745
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Herbicide Diphenyl ether Protoporphyrinogen Oxidase inhibitor	0	5	221	1743
1.0000000	0.0000000	0.0000000	6.7380194	1.0000000	Herbicide Imidazolinone Acetolactate synthase inhibitor	0	6	221	1742
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Herbicide N-Phenylimide Protoporphyrinogen Oxidase inhibitor	0	4	221	1744
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Herbicide Phenoxyacetic Auxin mimic	0	4	221	1744
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Herbicide Phenylurea Inhbition of photosynthesis at PSll	0	5	221	1743
0.6089194	0.0000000	0.0000000	4.6456988	1.0000000	Herbicide Thiocarbamate Very Long-Chain Fatty Acid Synthesis inhibitor	0	8	221	1740
0.6089194	0.0000000	0.0000000	4.6456988	1.0000000	Herbicide Triazine Inhibition of photosynthesis at PSll	0	8	221	1740
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	HMGCoA inhibitor	0	4	221	1744
0.3820522	0.0000000	0.0000000	2.8497280	1.0000000	Imidazolidines	0	12	221	1736
0.6237743	0.0000000	0.0000000	3.1560268	1.0000000	Insecticide Aliphatic organothiophosphate AChE Inhibitor	0	11	221	1737
0.3990497	0.0000000	0.0000000	2.2046417	1.0000000	Insecticide Aryl organothiophosphate AChE Inhibitor	0	15	221	1733
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Insecticide Arylalkyl organothiophosphate AChE Inhibitor	0	5	221	1743
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Insecticide Benzoylurea Chitin biosynthesis inhibitor	0	3	221	1745
0.3834890	0.0000000	0.0000000	2.5969826	1.0000000	Insecticide Carbamate AChE Inhibitor	0	13	221	1735
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Insecticide Diacylhydrazine Ecdysone receptor agonist	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Insecticide Nitroguanidine NACHR Competative Modulator	0	4	221	1744
1.0000000	0.0000000	0.0000000	6.7380194	1.0000000	Insecticide Organophosphate AChE Inhibitor	0	6	221	1742
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Insecticide Phosphoramidate AChE Inhibitor	0	5	221	1743
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Kinase inhibitor	0	4	221	1744
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Methoxybenzenes	0	3	221	1745
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Methoxyphenols	0	5	221	1743
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Neurokinin receptor antagonist	0	4	221	1744
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Nitrophenols	0	4	221	1744
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Organic carbonic acids and derivatives	0	3	221	1745
0.6089194	0.0000000	0.0000000	4.6456988	1.0000000	Organic cyanides	0	8	221	1740
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Organic metalloid salts	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Organic nitro compounds	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Organic nitroso compounds	0	4	221	1744
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Organobromides	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Organometallic Hg	0	3	221	1745
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Organometallic Sn	0	7	221	1741
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Organonitrogen compounds	0	4	221	1744
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Organosulfonic acids and derivatives	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Phenanthrenes and derivatives	0	3	221	1745
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Phenol ethers	0	7	221	1741
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Phenoxy compounds	0	3	221	1745
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Phenoxyacetic acid derivatives	0	7	221	1741
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Phenylhydrazines	0	3	221	1745
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Phosphodiesterase inhibitor	0	5	221	1743
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Phosphonic acid diesters	0	3	221	1745
1.0000000	0.0000000	0.0000000	5.5034107	1.0000000	Progestogen	0	7	221	1741
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Pyranones and derivatives	0	4	221	1744
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Pyrazoles	0	4	221	1744
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Pyridinecarboxylic acids and derivatives	0	4	221	1744
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Retinoid	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Serotonin receptor antagonist	0	4	221	1744
1.0000000	0.0000000	0.0000000	6.7380194	1.0000000	Silicon PFASs	0	6	221	1742
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Sodium channel inhibitor	0	3	221	1745
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Tetracarboxylic acids and derivatives	0	4	221	1744
1.0000000	0.0000000	0.0000000	12.0179052	1.0000000	Thioureas	0	4	221	1744
1.0000000	0.0000000	0.0000000	8.6580069	1.0000000	Triazinones	0	5	221	1743
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Vinyl chlorides	0	3	221	1745
1.0000000	0.0000000	0.0000000	19.1923382	1.0000000	Xylenes	0	3	221	1745

Table 5 of Truong et al. 

sig.classes <- lapply(res, function(df) {
  sig <- df %>% 
    filter(padj < 0.05 & (Odds_Ratio > 3 | Odds_Ratio < 1/3)) %>% 
    select(Pval, padj, Odds_Ratio, Lower, Upper, group, `Actives in group`, `Inactives in group`)
})

names(sig.classes) <- aenm.abbrevs

add.assay <- Map(function(df, name) {
  df$assay <- name
  df <- df[, c("assay", colnames(df)[colnames(df) != "assay"])]
  return(df)
}, sig.classes, names(sig.classes))

tb.paper <- bind_rows(add.assay)

# report pvalues with 2 sigfigs 
tb.paper[, c("Pval", "padj")] <- signif(tb.paper[, c("Pval", "padj")], digits = 2)

# round other numerical values to 2 digits after decimal pt 
tb.paper[, c("Odds_Ratio", "Lower", "Upper")] <- round(tb.paper[, c("Odds_Ratio", "Lower", "Upper")], digits = 2)
kable(tb.paper,  caption = "Summary of Significant Results across all Targets")

Summary of Significant Results across all Targets

assay	Pval	padj	Odds_Ratio	Lower	Upper	group	Actives in group	Inactives in group
DIO1	2.3e-05	0.0034	42.71	5.15	1950.44	Estrogen flavonoid	6	1
DIO1	3.9e-05	0.0034	16.68	3.78	100.72	Quaternary ammonium salts	7	3
DIO1	8.3e-05	0.0048	21.36	3.79	216.95	Herbicide Chloroacetamide Very Long-Chain Fatty Acid Synthesis inhibitor	6	2
DIO1	5.0e-04	0.0220	10.67	2.51	51.83	Estrogen nonsteroidal	6	4
DIO1	1.1e-03	0.0320	28.24	2.78	1384.87	Antibiotic polyketide	4	1
DIO1	1.1e-03	0.0320	28.24	2.78	1384.87	Insecticide Arylalkyl organothiophosphate AChE Inhibitor	4	1
DIO1	2.0e-03	0.0430	Inf	2.90	Inf	Aryl chlorides	3	0
DIO1	2.0e-03	0.0430	Inf	2.90	Inf	Fungicide Phthalimide Multi-site activity	3	0
DIO2	2.4e-05	0.0021	35.54	4.54	1591.59	Herbicide Chloroacetamide Very Long-Chain Fatty Acid Synthesis inhibitor	7	1
DIO2	1.9e-05	0.0021	20.35	4.04	197.16	Estrogen nonsteroidal	8	2
DIO2	2.6e-04	0.0150	11.83	2.68	71.28	Quaternary ammonium salts	7	3
DIO2	6.2e-04	0.0270	8.87	2.24	41.57	Bisphenol	7	4
DIO3	2.6e-05	0.0023	35.02	4.47	1568.38	Herbicide Chloroacetamide Very Long-Chain Fatty Acid Synthesis inhibitor	7	1
DIO3	2.6e-05	0.0023	35.02	4.47	1568.38	Herbicide Triazine Inhibition of photosynthesis at PSll	7	1
DIO3	2.8e-04	0.0160	11.66	2.64	70.19	Quaternary ammonium salts	7	3
DIO3	6.6e-04	0.0290	8.74	2.21	40.99	Bisphenol	7	4
IYD	6.1e-06	0.0011	28.46	5.37	280.64	Insecticide Chlorinated cyclodiene GABA-gated chloride channel blocker	7	2
IYD	2.3e-05	0.0020	5.39	2.43	11.59	PFAAs	13	20
IYD	1.2e-04	0.0069	16.19	3.43	100.84	Quaternary ammonium salts	6	3
IYD	5.3e-04	0.0230	9.70	2.45	40.59	Bisphenol	6	5
IYD	9.6e-04	0.0340	8.09	2.14	30.54	1-hydroxy-2-unsubstituted benzenoids	6	6

Supplemental File 2

# prep Excel output with tabs 
names(res)  <- paste0(aenm.abbrevs, "-class")
res$`class annotations` = classified_dt 

Hits by Target

# organize based on odds ratios 
inf.or <- c("Aryl chlorides", "Fungicide Phthalimide Multi-site activity")
sig.or <- c("Quaternary ammonium salts", "Herbicide Chloroacetamide Very Long-Chain Fatty Acid Synthesis inhibitor", 
            "Estrogen nonsteroidal", "Bisphenol", 
            "Estrogen flavonoid", "Antibiotic polyketide", 
            "Insecticide Arylalkyl organothiophosphate AChE Inhibitor", 
            "Herbicide Triazine Inhibition of photosynthesis at PSll", 
            "Insecticide Chlorinated cyclodiene GABA-gated chloride channel blocker", "PFAAs", 
            "1-hydroxy-2-unsubstituted benzenoids")
  
# helper function to draw the Venn Diagram for an input class 
# this only counts chemicals that were uniformly tested across all 4 targets 
#' @hitc.class.dat is a dataframe or (data.table) with columns for DTXSID, classifications, aenm, and hitc
#' @class_var is the name (of character type) of the column corresponding to classifications
display_venn <- function(class, hitc.class.dat, class_var) {
  merged_datw <- dcast(hitc.class.dat, as.formula(paste("dsstox_substance_id +", class_var, "~ aenm")), 
                       value.var = 'hitc')
  setDT(merged_datw)
  merged_datw$name <- classified_dt$name[match(merged_datw$dsstox_substance_id, classified_dt$dsstox_substance_id)]
  
  colnames(merged_datw)[colnames(merged_datw)%in% h.deiod.aenm] <- aenm.abbrevs
  merged_datw[, total_hits := DIO1 + DIO2 + DIO3 + IYD]
  merged_datw.tested4x <- merged_datw[complete.cases(merged_datw)]
  
  class_dat <- merged_datw.tested4x[get(class_var) == class]
  hit.freqs <- table(class_dat$total_hits)
  
  list_venn <- list(DIO1 = class_dat[DIO1 == 1, name], 
                  DIO2 = class_dat[DIO2 == 1, name], 
                  DIO3 = class_dat[DIO3 == 1, name], 
                  IYD = class_dat[IYD == 1, name])
  
  venn_obj <- ggvenn(list_venn, 
       show_percentage = FALSE, 
       fill_color = c("#0073C2FF", "#EFC000FF", "#868686FF", "#CD534CFF"),
       text_size = 6) +
  annotate("text", x = 2, y = -0.5, label = ifelse(!is.na(hit.freqs["0"]), hit.freqs["0"], ""), 
           size = 6)
  
  return(venn_obj)
}

Odds Ratio == Inf

merged_dat.sel <- merge.data.table(long_hitc_final,
                        classified_dt[,.(dsstox_substance_id,name,class_type,chosen_class)],
                               by = c("dsstox_substance_id"),
                               all.x = T)

infor_list <- lapply(inf.or, display_venn, hitc.class.dat = merged_dat, class_var = "chosen_class")
names(infor_list) <- inf.or

# combine the plots into one figure
ggarrange(infor_list$`Aryl chlorides`, infor_list$`Fungicide Phthalimide Multi-site activity`,
          labels = names(infor_list),
          font.label = list(size = 18),
          hjust = -0.25, 
          label.y = 0.8,
          nrow = 1, ncol = 2)

Odds Ratio > 3

sigor_list <- lapply(sig.or, display_venn, hitc.class.dat = merged_dat, class_var = "chosen_class")
names(sigor_list) <- sig.or

sig.class.labels <- names(sigor_list)

# combine the plots into one figure
ggarrange(plotlist = sigor_list, 
          labels = sig.class.labels,
          label.y = 0.97,
          label.x = c(0, -0.20, 0.05, 0.10, 0.05, 0, -0.10, -0.08, -0.15, 0.15, -0.05),
          hjust = -0.25,
          nrow = 6, ncol = 2)

Figure 4 of Truong et al. 

# focus on triazines and estrogen flavonoids for paper
flavos.venn <- sigor_list$`Estrogen flavonoid` + 
  annotate("text", x = 0, y = -2, label = "Estrogen flavonoids",
            size = 6, fontface= "bold") 

triazine.venn <- sigor_list$`Herbicide Triazine Inhibition of photosynthesis at PSll` +
  annotate("text", x = 0, y = -2, label = "Herbicide Triazines Inhibition of photosynthesis at PSll",
            size = 6, fontface= "bold") 

uniq.positives <- ggarrange(flavos.venn, triazine.venn,
          labels = c("A", "B"),
          font.label = list(size = 25),
          label.x = 0,
          label.y = 0.8,
          hjust = 0,
          nrow = 1, ncol = 2)

uniq.positives

ggsave(plot = uniq.positives,
       units = "in",
       dpi = 300,
       width = 15, height = 12,
       device = "tiff",
       filename = "./figures/300dpi/uniq_positives.tiff")

ggsave(plot = uniq.positives,
       units = "in",
       dpi = 300,
       width = 15, height = 12,
       device = "png",
       filename = "./figures/uniq_positives.png")

Color/Spectral Interference

We wish to examine whether there is enriched activity (or inactivity) for specific groups of colored substances (e.g. C.I., FD&C, D&C, based on the specific color).

Colors vs. non-colors

Color breakdown in the DIO/IYD testing library.

is_color <- grepl("\\w+\\s(red|orange|yellow|green|blue|violet|black)\\s*\\w*", classified_dt$name, ignore.case = T)
classified_dt[!is_color, main_class := chosen_class]
classified_dt[is_color, main_class := "Colors"]

classified_dt[, new_class := chosen_class]

all_colors <- c("Red", "Orange", "Yellow", "Green", "Blue", "Violet", "Black")

for(k in seq_along(all_colors)) {
  classified_dt$new_class[which(grepl(paste0("\\w+\\s(", all_colors[k], ")\\s*\\w*"), classified_dt$name, ignore.case = T))] = all_colors[k]
}

# how many of each specific color 
classified_dt[main_class == "Colors", .N, by = .(main_class, new_class)]

M.class2 <- as.data.frame.matrix(table(classified_dt$dsstox_substance_id, 
                                           classified_dt$main_class))

res2 <- RunFisherTests(M.hitc2, M.class2[, "Colors", drop = FALSE], "group")
names(res2) <- aenm.abbrevs

res2 <- Map(function(df, name) {
  df$assay <- name
  df <- df[, c("assay", colnames(df)[colnames(df) != "assay"])]
  return(df)
}, res2, names(res2))

all_res <- bind_rows(res2)

Results for colors vs. non-colors

For all assays

assay	Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
DIO1	0.2678900	1.690450	0.5613094	4.278143	0.2678900	Colors	6	25	240	1691
DIO2	0.0007306	3.701625	1.6494181	8.082131	0.0007306	Colors	13	18	315	1616
DIO3	0.0029699	3.177040	1.3917025	6.972719	0.0029699	Colors	12	19	320	1611
IYD	0.0000067	6.353009	2.7948141	14.119985	0.0000067	Colors	13	17	208	1731

Venn Diagrams show results before and after applying a “selectivity” filter.

Color-specific classes

M.class3 <- as.data.frame.matrix(table(classified_dt$dsstox_substance_id, 
                                           classified_dt$new_class))

res3 <- RunFisherTests(M.hitc2, M.class3[, all_colors], "group")
names(res3) <- aenm.abbrevs

DIO1

For DIO1

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.1671538	3.5045293	0.3154710	24.601313	0.6686153	Orange	2	4	244	1712
0.4885849	1.7463273	0.0353301	17.735712	0.9771698	Blue	1	4	245	1712
1.0000000	1.1631568	0.0251881	9.649539	1.0000000	Red	1	6	245	1710
1.0000000	0.9965032	0.0220218	7.810076	1.0000000	Yellow	1	7	245	1709

DIO2

For DIO2

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0355920	7.520028	0.8579640	90.49250	0.1423681	Blue	3	2	325	1632
0.0961341	3.757931	0.5479218	22.32509	0.1805402	Red	3	4	325	1630
0.1354052	3.005085	0.4643878	15.52862	0.1805402	Yellow	3	5	325	1629
0.2643525	2.498471	0.2251265	17.51444	0.2643525	Orange	2	4	326	1630

DIO3

For DIO3

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0644797	4.939448	0.6586628	37.039787	0.1980649	Orange	3	3	329	1627
0.0990325	3.703190	0.5399719	21.998725	0.1980649	Red	3	4	329	1626
0.2010154	3.284110	0.2733031	28.790320	0.2680205	Blue	2	3	330	1627
0.6297011	1.639916	0.1611829	9.222986	0.6297011	Yellow	2	6	330	1624

IYD

For IYD

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0002965	20.142792	3.2738241	212.224944	0.0011859	Red	5	2	216	1746
0.0019318	16.046253	2.2845934	178.150291	0.0038636	Blue	4	2	217	1746
0.0997871	5.304231	0.4407893	46.544510	0.1330495	Orange	2	3	219	1745
1.0000000	0.000000	0.0000000	5.503411	1.0000000	Yellow	0	7	221	1741

sig.colors <- c("Red", "Blue")

new.merged.colors2 <- merge.data.table(long_hitc_final, 
                               classified_dt[, .(dsstox_substance_id,class_type,new_class)], 
                               by = c("dsstox_substance_id"), 
                               all.x = T)

new.merged.colors2.sel <- merge.data.table(long_hitc_final2, 
                               classified_dt[, .(dsstox_substance_id,class_type,new_class)], 
                               by = c("dsstox_substance_id"), 
                               all.x = T)

# before selectivity filter 
sig.iyd.colors <- lapply(sig.colors, display_venn, hitc.class.dat = new.merged.colors2, class_var = "new_class")
names(sig.iyd.colors) <- sig.colors

# combine the plots into one figure
ggarrange(plotlist = sig.iyd.colors, 
          labels = names(sig.iyd.colors),
          font.label = list(size = 20),
          nrow = 1, ncol = 2)

# after selectivity filter 
sig.iyd.colors2 <- lapply(sig.colors, display_venn, hitc.class.dat = new.merged.colors2.sel, class_var = "new_class")
names(sig.iyd.colors2) <- sig.colors

# combine the plots into one figure
ggarrange(plotlist = sig.iyd.colors2, 
          labels = names(sig.iyd.colors2),
          font.label = list(size = 20),
          nrow = 1, ncol = 2)

Venn Diagrams show results before and after applying a “selectivity” filter.

Registered classes

classified_dt[, new_class := chosen_class]
classified_dt[grep("^[F]*D&C", classified_dt$name), 
              new_class := "(F)D&C"]
classified_dt[grep("C.I.", classified_dt$name), new_class := "C.I."]

M.class4 <- as.data.frame.matrix(table(classified_dt$dsstox_substance_id, 
                                           classified_dt$new_class))

res4 <- RunFisherTests(M.hitc2, M.class4[, c("(F)D&C", "C.I.")], "group")
names(res4) <- aenm.abbrevs

DIO1

DIO1: For registered classes

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.3311025	3.494327	0.0590515	67.456250	0.345855	(F)D&C	1	2	245	1714
0.3458550	1.558808	0.3805507	4.786131	0.345855	C.I.	4	18	242	1698

DIO2

DIO2: For registered classes

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.4225349	2.493889	0.0421695	48.025744	0.4225349	(F)D&C	1	2	327	1632
0.2429139	1.883513	0.5989874	5.115433	0.4225349	C.I.	6	16	322	1618

DIO3

DIO3: For registered classes

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0802724	2.317707	0.7929122	6.096793	0.1605447	C.I.	7	15	325	1615
0.4267680	2.457913	0.0415593	47.330155	0.4267680	(F)D&C	1	2	331	1628

IYD

IYD: For registered classes

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0348474	15.909106	0.8250675	935.453717	0.0348474	(F)D&C	2	1	219	1747
0.0186756	3.453165	1.0759729	9.689231	0.0348474	C.I.	6	14	215	1734

Venn Diagrams show results before and after applying a “selectivity” filter.

ToxPrint Enrichment

load ToxPrints

toxprints <- fread("./data/DIO_IYD_testlib_invitrodb_v3_5_input_toxprints.csv")

# how many chems don't have ToxPrints?
head(toxprints[cid == ""])

nrow(toxprints[cid == ""])

## [1] 82

82 chemicals did not have ToxPrints because they were either UVCBs or Markush structures.

form matrices

# subset to available ToxPrints 
chemotype.cols <- colnames(toxprints)[colnames(toxprints) %notin% c("DTXSID", "smiles", "cid","M_COMPOUND_HISTORY_[STRING]","M_CORINA_SYMPHONY_ERRORS_[STRING]")]
M.chemotype.dt <- toxprints[cid != "", c("DTXSID", ..chemotype.cols)]

# add chemical names and classifications
M.chemotype.dt$name <- classified_dt$name[match(M.chemotype.dt$DTXSID, classified_dt$dsstox_substance_id)]
M.chemotype.dt$chosen_class <- classified_dt$chosen_class[match(M.chemotype.dt$DTXSID, classified_dt$dsstox_substance_id)]
M.chemotype.dt <- M.chemotype.dt[, c("DTXSID", "name", "chosen_class", chemotype.cols), with = FALSE]

M.chemotype <- as.data.frame(M.chemotype.dt[, c("DTXSID", ..chemotype.cols)])
rownames(M.chemotype) <- M.chemotype$DTXSID
M.chemotype <- M.chemotype[, -1]

M.hitc.tp <- M.hitc2[rownames(M.chemotype),]

# check that rows are ordered the same
identical(rownames(M.hitc.tp), rownames(M.chemotype))

## [1] TRUE

run tests

tp.res <- RunFisherTests(M.hitc.tp, M.chemotype, "group")

significant for DIO1

For DIO1

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0000003	6.9669239	3.2687022	14.7167791	0.0000514	bond:CX_halide_alkyl-F_perfluoro_octyl	16	18	209	1641
0.0000002	3.4984119	2.1773331	5.5215907	0.0000514	chain:alkaneLinear_octyl_C8	32	75	193	1584
0.0000020	5.6873891	2.7449749	11.5462980	0.0001397	chain:alkaneLinear_dodedyl_C12	16	22	209	1637
0.0000021	3.9012815	2.2114203	6.7149118	0.0001397	bond:S~N_generic	23	47	202	1612
0.0000128	3.0928471	1.8599708	5.0219248	0.0006373	bond:CS_sulfide	27	70	198	1589
0.0000234	Inf	6.8428548	Inf	0.0010354	bond:CC(=O)C_ketone_alkene_cyclic_3-en-1-one	5	0	220	1659
0.0000278	17.6687140	3.9985962	106.8452637	0.0011075	ring:hetero_[6_6]O_benzopyrone(1_4-)	7	3	218	1656
0.0000407	3.7054775	1.9526794	6.7980594	0.0014777	chain:alkaneLinear_decyl_C10	18	38	207	1621
0.0000458	5.0181293	2.2586326	10.7814549	0.0015241	bond:C(Z)C~Q_a-halocarbonyl	13	20	212	1639
0.0000780	7.6238012	2.6496526	21.9361668	0.0023944	bond:COH_alcohol_alkene_cyclic	9	9	216	1650
0.0001330	6.8576442	2.4360529	19.0101566	0.0035369	bond:COH_alcohol_alkene	9	10	216	1649
0.0001330	6.8576442	2.4360529	19.0101566	0.0035369	chain:alkaneLinear_tetradecyl_C14	9	10	216	1649
0.0001818	3.1887244	1.7006498	5.7586006	0.0045340	bond:CC(=O)C_ketone_aromatic_aliphatic	18	44	207	1615
0.0005295	4.2075966	1.7947711	9.3625444	0.0111188	chain:alkeneLinear_mono-ene_2-hexene	11	20	214	1639
0.0006106	0.2546282	0.0804518	0.6190398	0.0121817	bond:COH_alcohol_pri-alkyl	5	136	220	1523
0.0009620	12.5130686	2.4156834	81.1098542	0.0159968	chain:alkeneLinear_diene_1_3-butene	5	3	220	1656
0.0009620	12.5130686	2.4156834	81.1098542	0.0159968	chain:aromaticAlkane_Ph-C6	5	3	220	1656
0.0011563	3.0760336	1.5030017	5.9793331	0.0177449	chain:alkeneLinear_mono-ene_ethylene	14	35	211	1624
0.0012792	5.0526836	1.7704970	13.6213554	0.0189035	bond:COC_ether_alkenyl	8	12	217	1647
0.0020777	3.1636597	1.4476363	6.5077946	0.0259066	chain:alkeneLinear_diene_1_2-butene	12	29	213	1630
0.0021747	3.3561406	1.4687740	7.1928148	0.0262943	bond:P~S_generic	11	25	214	1634
0.0035329	7.5035291	1.7122854	32.8867893	0.0369759	bond:quatN_alkyl_acyclic	5	5	220	1654
0.0035580	5.6451779	1.5985659	18.7493122	0.0369759	bond:P=O_phosphate_thioate	6	8	219	1651
0.0036142	4.0362527	1.4639427	10.2827353	0.0369759	ring:hetero_[6_6]_O_benzopyran	8	15	217	1644

DIO2

For DIO2

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0000000	3.8791047	2.7102386	5.5241299	0.0000000	chain:alkeneLinear_mono-ene_ethylene_generic	64	102	239	1479
0.0000000	8.2583641	4.2222558	16.5282448	0.0000000	chain:alkeneLinear_diene_1_2-butene	25	17	278	1564
0.0000000	7.3806821	3.8454275	14.3890051	0.0000000	chain:alkeneLinear_mono-ene_allyl	25	19	278	1562
0.0000000	6.6162143	3.5945830	12.2726339	0.0000000	chain:alkeneLinear_mono-ene_ethylene	27	23	276	1558
0.0000000	8.0202751	3.9998120	16.4658296	0.0000001	chain:aromaticAlkene_Ph-C2_acyclic_generic	23	16	280	1565
0.0000000	10.0682544	4.5406267	23.5249928	0.0000001	chain:alkeneLinear_mono-ene_2-hexene	20	11	283	1570
0.0000001	3.2840940	2.1091317	5.0572028	0.0000058	chain:alkaneLinear_octyl_C8	39	68	264	1513
0.0000001	5.5403773	2.8831734	10.6483908	0.0000061	chain:alkeneBranch_mono-ene_2-butene	22	22	281	1559
0.0000002	7.0575868	3.2746823	15.5153426	0.0000079	chain:aromaticAlkene_Ph-C2	18	14	285	1567
0.0000009	5.4924565	2.7144441	11.1123079	0.0000371	chain:alkaneLinear_dodedyl_C12	19	19	284	1562
0.0000058	3.4362598	1.9876198	5.8443342	0.0001916	chain:aromaticAlkane_Ar-C-Ar	26	42	277	1539
0.0000190	4.8349690	2.2774124	10.1787384	0.0005411	bond:CX_halide_alkyl-F_perfluoro_octyl	16	18	287	1563
0.0000190	3.5589012	1.9517783	6.3703069	0.0005411	chain:alkaneLinear_decyl_C10	22	34	281	1547
0.0000352	7.3946512	2.6829540	21.3689856	0.0009374	chain:alkaneLinear_tetradecyl_C14	11	8	292	1573
0.0000583	4.5174117	2.0930704	9.6143457	0.0013681	bond:C(Z)C~Q_a-halocarbonyl	15	18	288	1563
0.0000622	3.1618973	1.7775869	5.5076528	0.0013796	chain:aromaticAlkane_Ph-C1-Ph	23	40	280	1541
0.0001312	8.0226137	2.5280844	27.5934363	0.0026167	chain:aromaticAlkene_Ph-C2_styrene	9	6	294	1575
0.0003474	15.9139244	2.8280562	161.7999170	0.0057755	chain:alkeneLinear_diene_1_3-butene	6	2	297	1579
0.0006580	Inf	3.4665591	Inf	0.0100971	chain:alkeneLinear_diene_1_4-diene	4	0	299	1581
0.0025919	0.0000000	0.0000000	0.5229921	0.0287271	chain:oxy-alkaneLinear_ethyleneOxide_EO1	0	38	303	1543
0.0028712	21.0798358	2.0770524	1035.1553444	0.0293747	chain:aromaticAlkane_Ph-C8	4	1	299	1580
0.0028712	21.0798358	2.0770524	1035.1553444	0.0293747	ring:hetero_[5]_N_O_oxazole	4	1	299	1580
0.0041254	Inf	2.1644404	Inf	0.0299278	bond:metal_group_III_other_generic_oxy	3	0	300	1581
0.0041254	Inf	2.1644404	Inf	0.0299278	bond:metal_group_III_other_Sn_oxy	3	0	300	1581
0.0038371	8.8077550	1.7036013	57.0336927	0.0299278	atom:element_metal_poor_metal	5	3	298	1578
0.0038371	8.8077550	1.7036013	57.0336927	0.0299278	bond:metal_group_III_other_generic	5	3	298	1578
0.0038371	8.8077550	1.7036013	57.0336927	0.0299278	bond:metal_group_III_other_Sn_generic	5	3	298	1578
0.0038371	8.8077550	1.7036013	57.0336927	0.0299278	bond:metal_group_III_other_Sn_organo	5	3	298	1578
0.0038371	8.8077550	1.7036013	57.0336927	0.0299278	chain:aromaticAlkane_Ph-C6	5	3	298	1578
0.0037180	6.3579572	1.6052026	26.5197275	0.0299278	bond:C=N_imine_C(connect_H_gt_0)	6	5	297	1576
0.0052633	0.1879874	0.0220827	0.7196057	0.0355943	bond:NC=O_urea_generic	2	54	301	1527
0.0060654	0.0000000	0.0000000	0.6292167	0.0396738	ring:hetero_[6]_Z_1_3_5-	0	32	303	1549
0.0075062	6.6045819	1.4125828	33.4729929	0.0467966	chain:alkaneLinear_hexadecyl_C16	5	4	298	1577

DIO3

For DIO3

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0000000	9.979855	5.049863	20.4549217	0.0000000	chain:alkeneLinear_diene_1_2-butene	27	15	281	1561
0.0000000	9.730911	5.011287	19.5230411	0.0000000	chain:alkeneLinear_mono-ene_allyl	28	16	280	1560
0.0000000	8.380412	4.531345	15.8093851	0.0000000	chain:alkeneLinear_mono-ene_ethylene	30	20	278	1556
0.0000000	3.563973	2.486190	5.0811820	0.0000000	chain:alkeneLinear_mono-ene_ethylene_generic	62	104	246	1472
0.0000000	9.410691	4.611044	19.9305420	0.0000000	chain:alkaneLinear_dodedyl_C12	24	14	284	1562
0.0000000	3.829697	2.482839	5.8620383	0.0000001	chain:alkaneLinear_octyl_C8	43	64	265	1512
0.0000000	4.250222	2.641912	6.7905069	0.0000001	chain:alkeneCyclic_ethene_C_(connect_noZ)	37	49	271	1527
0.0000000	5.521004	3.099257	9.8370451	0.0000001	chain:alkaneLinear_decyl_C10	28	28	280	1548
0.0000004	5.682822	2.839648	11.4140247	0.0000133	chain:aromaticAlkene_Ph-C2_acyclic_generic	20	19	288	1557
0.0000008	6.507859	2.982385	14.4385998	0.0000277	chain:alkeneLinear_mono-ene_2-hexene	17	14	291	1562
0.0000023	3.359957	2.021174	5.5083548	0.0000714	chain:alkeneCyclic_diene_cyclohexene	30	49	278	1527
0.0000051	9.068142	3.260741	27.4159650	0.0001449	chain:alkaneLinear_tetradecyl_C14	12	7	296	1569
0.0000088	5.335365	2.467222	11.5386125	0.0002347	chain:aromaticAlkene_Ph-C2	16	16	292	1560
0.0000186	4.074418	2.091517	7.8191944	0.0004633	chain:alkeneBranch_mono-ene_2-butene	19	25	289	1551
0.0000203	36.548549	4.665020	1636.6100700	0.0004756	chain:alkeneLinear_diene_1_3-butene	7	1	301	1575
0.0000249	3.485457	1.911965	6.2378162	0.0005512	bond:CC(=O)C_ketone_alkene_generic	22	34	286	1542
0.0000711	4.426161	2.051136	9.4207576	0.0013514	bond:C(Z)C~Q_a-halocarbonyl	15	18	293	1558
0.0001136	Inf	4.731093	Inf	0.0020608	bond:CC(=O)C_ketone_alkene_cyclic_3-en-1-one	5	0	303	1576
0.0001498	7.860822	2.478289	27.0567197	0.0025981	chain:aromaticAlkene_Ph-C2_styrene	9	6	299	1570
0.0002420	5.262442	2.048169	13.5262546	0.0040226	bond:C=O_carbonyl_ab-unsaturated_aliphatic_(michael_acceptors)	11	11	297	1565
0.0002747	5.834320	2.110606	16.3759101	0.0043848	ring:hetero_[6]N_triazine(1_3_5-)	10	9	298	1567
0.0003075	3.898234	1.786992	8.3032824	0.0047195	bond:CN_amine_sec-NH_aromatic_aliphatic	14	19	294	1557
0.0006275	4.447916	1.785643	10.8762554	0.0089419	bond:CC(=O)C_ketone_alkene_cyclic_(C6)	11	13	297	1563
0.0015337	0.000000	0.000000	0.5127945	0.0185440	chain:oxy-alkaneLinear_ethyleneOxide_EO1	0	38	308	1538
0.0030590	20.668647	2.036520	1015.0463315	0.0332759	bond:CS_sulfide_di-	4	1	304	1575

IYD

For IYD

Pval	Odds_Ratio	Lower	Upper	padj	group	Actives in group	Inactives in group	Actives not in group	Inactives not in group
0.0000000	4.9942140	3.3304177	7.4245940	0.0000000	chain:alkaneLinear_hexyl_C6	48	101	151	1589
0.0000000	4.9562291	3.1227718	7.7620942	0.0000000	chain:alkaneLinear_octyl_C8	36	72	163	1618
0.0000000	3.6240711	2.5012830	5.2048035	0.0000000	bond:COH_alcohol_aromatic_phenol	55	161	144	1529
0.0000000	3.5271137	2.4363760	5.0612674	0.0000000	bond:COH_alcohol_aromatic	55	165	144	1525
0.0000000	9.8027077	4.8655341	19.8175449	0.0000000	chain:alkaneLinear_dodedyl_C12	20	19	179	1671
0.0000000	5.8674615	3.2031085	10.5518504	0.0000009	chain:alkaneLinear_decyl_C10	22	35	177	1655
0.0000002	14.0262807	4.8981213	43.2143635	0.0000114	chain:alkaneLinear_tetradecyl_C14	11	7	188	1683
0.0000004	4.7385049	2.5987761	8.4193362	0.0000179	chain:aromaticAlkane_Ph-C1-Ph	21	41	178	1649
0.0000010	61.1914290	7.8098323	2730.6008204	0.0000380	chain:aromaticAlkane_Ph-C6	7	1	192	1689
0.0000018	4.2114705	2.3311105	7.3932555	0.0000637	chain:aromaticAlkane_Ar-C-Ar	21	46	178	1644
0.0000119	20.4316996	4.6182487	123.0511490	0.0003382	bond:CX_halide_alkyl-X_bicyclo[2_2_1]heptene	7	3	192	1687
0.0000228	11.7242160	3.5253028	41.4637390	0.0005675	chain:aromaticAlkane_Ph-C4	8	6	191	1684
0.0000386	6.1108167	2.5244242	14.2660852	0.0009071	bond:QQ(Q~O_S)_sulfur_oxide	11	16	188	1674
0.0000484	7.9396561	2.8168589	22.0472001	0.0010725	bond:CX_halide_alkenyl-X_dihalo_(1_2-)	9	10	190	1680
0.0000910	4.8584283	2.1547050	10.4480707	0.0018148	bond:CX_halide_alkyl-F_perfluoro_octyl	12	22	187	1668
0.0000867	3.1408561	1.7474562	5.4464545	0.0018148	bond:CX_halide_alkyl-F_perfluoro_hexyl	20	58	179	1632
0.0001454	3.5128502	1.8025456	6.5501727	0.0026369	bond:S(=O)O_sulfonicAcid_generic	16	41	183	1649
0.0003470	3.0609374	1.6195649	5.5354168	0.0046674	bond:S(=O)O_sulfonate	17	50	182	1640
0.0004588	3.6174435	1.7109027	7.2369633	0.0059047	ring:fused_[6_6]_naphthalene	13	32	186	1658
0.0005497	34.4808487	3.3930421	1688.9476331	0.0062669	chain:aromaticAlkane_Ph-C8	4	1	195	1689
0.0005309	14.4502204	2.7871849	93.7818426	0.0062669	chain:alkaneLinear_hexadecyl_C16	5	3	194	1687
0.0005435	5.8462415	2.0459610	15.7784622	0.0062669	bond:CX_halide_alkyl-X_tertiary	8	12	191	1678
0.0005213	3.8044007	1.7318354	7.8824282	0.0062669	bond:CX_halide_alkyl-Cl_dichloro_(1_1-)	12	28	187	1662
0.0006480	6.7965890	2.1254497	20.7701255	0.0071819	bond:S(=O)O_sulfonicEster_aliphatic_(S-C)	7	9	192	1681
0.0007996	5.3946177	1.9125579	14.2479120	0.0083956	bond:N=N_azo_aromatic	8	13	191	1677
0.0010833	4.0072059	1.6675067	8.9785047	0.0110832	bond:S(=O)O_sulfonicAcid_cyclic_(ring)	10	22	189	1668
0.0011444	5.0068352	1.7954990	12.9822859	0.0114156	bond:N=N_azo_generic	8	14	191	1676
0.0014985	5.5558536	1.8038121	15.9073488	0.0142361	bond:S(=O)O_sulfuricAcid_generic	7	11	192	1679
0.0019995	8.6681161	1.9756255	38.0134631	0.0184841	bond:quatN_alkyl_acyclic	5	5	194	1685
0.0021638	5.0904598	1.6769590	14.2277197	0.0191855	bond:quatN_generic	7	12	192	1678
0.0024617	3.2347852	1.4380324	6.7730879	0.0204628	chain:aromaticAlkene_Ph-C2_acyclic_generic	11	30	188	1660
0.0028093	5.7973342	1.6788471	18.4604929	0.0228757	bond:S(=O)O_sulfonicEster_acyclic_(S-C(ring))	6	9	193	1681
0.0030329	3.1282333	1.3949072	6.5223950	0.0241085	bond:CX_halide_alkenyl-X_generic	11	31	188	1659
0.0036419	0.3043281	0.0960131	0.7418166	0.0279449	bond:C(=O)O_carboxylicEster_acyclic	5	132	194	1558
0.0052649	6.1855589	1.5326626	22.8882654	0.0389016	bond:C=N_imine_N(connect_noZ)	5	7	194	1683

Update Supplemental File 2

names(tp.res) <- paste0(aenm.abbrevs, "-CT")
tp.res$chemotypes <- toxprints

write.xlsx(c(res,tp.res), file = "./tables/Supp2_Class&ToxPrint_Enrichment_AllResults.xlsx")

compile results across targets

sig.list <- Map(function(df, name) {
  df$target <- name
  df <- df[, c("target", "Odds_Ratio", "padj", "group", "Actives in group", "Inactives in group", "Actives not in group", "Inactives not in group")]
  return(df)
}, sig.res, names(sig.res))

sig.tp.all <- bind_rows(sig.list)
setDT(sig.tp.all)
setnames(sig.tp.all, "group", "chemotype")

M.padj <- as.data.frame(dcast(sig.tp.all, chemotype ~ target, value.var = "padj"))
rownames(M.padj) <- M.padj$chemotype
M.padj <- M.padj[, -1]

M.or <- as.data.frame(dcast(sig.tp.all, chemotype ~ target, value.var = "Odds_Ratio"))
rownames(M.or) <- M.or$chemotype
M.or <- M.or[, -1]

identical(rownames(M.padj), rownames(M.or))

## [1] TRUE

cat("Total number of chemotypes found to be significantly enriched: ", length(sig.tp.all$chemotype))

## Total number of chemotypes found to be significantly enriched:  117

cat("Total number of unique chemotypes found to be significantly enriched: ", length(unique(rownames(M.padj))))

## Total number of unique chemotypes found to be significantly enriched:  77

# enriched for actives = 1; not enriched for actives = 0
M.active = M.or 
M.active[M.active > 3] = 1 
M.active[M.active < 1/3] = 0
M.active[is.na(M.active)] = 0
rs.active <- rowSums(M.active)
M.active <- M.active[rs.active > 0, ]
rs.active <- rowSums(M.active)
head(M.active)

cat("Total number of enriched chemotypes for actives:", nrow(M.active))

## Total number of enriched chemotypes for actives: 72

# enriched for inactives = 1; not enriched for inactives = 0 
M.inactive = M.or
M.inactive[M.inactive < 1/3] = 1
M.inactive[M.inactive > 3] = 0 
M.inactive[is.na(M.inactive)] = 0 
rs.inactive <- rowSums(M.inactive)
M.inactive <- M.inactive[rs.inactive > 0, ]
rs.inactive <- rowSums(M.inactive)
M.inactive 

cat("Total number of enriched chemotypes for inactives:", nrow(M.inactive))

## Total number of enriched chemotypes for inactives: 5

• 729 total chemotypes in ToxPrints
• A total of 117 chemotypes (77 unique chemotypes) were found to be significant across the assays.
  • 72 chemotypes were found to be enriched in the active space.
  • 5 chemotypes were found to be enriched in the inactive space.

pan-active for DIO1/2/3/IYD

M.active[rs.active == 4, ]

pan-active for 3 targets

M.active[rs.active == 3, ]

pan-active for 2 targets

M.active[rs.active == 2, ]

active just for DIO1

subset(M.active, DIO1 == 1 & DIO2 == 0 & DIO3 == 0 & IYD == 0)

active just for DIO2

subset(M.active, DIO1 == 0 & DIO2 == 1 & DIO3 == 0 & IYD == 0)

active just for DIO3

subset(M.active, DIO1 == 0 & DIO2 == 0 & DIO3 == 1 & IYD == 0)

active just for IYD

subset(M.active, DIO1 == 0 & DIO2 == 0 & DIO3 == 0 & IYD == 1)

Pan-Activity

calculate selectivity

# to select for the most selective hits for each ToxPrints enrichment case
for (i in 1:length(h.deiod.aenm)) {
  mc.deiod[aenm == h.deiod.aenm[i], assay := names(h.deiod.aenm)[i] ]
}
acc_wide <- dcast(mc.deiod, dsstox_substance_id + chnm ~ assay, value.var = "modl_acc")
setDT(acc_wide)
acc_wide$cytomed <- cytotox$cytotox_median_log[match(acc_wide$dsstox_substance_id, cytotox$dsstox_substance_id)]
acc_wide[is.na(cytomed), cytomed := 3]
colnames(acc_wide)[3:6] <- paste0(aenm.abbrevs, "_acc")

# probably more concise way to write this but works 
acc_wide[, DIO1_selectivity := cytomed - pmin(DIO1_acc, 5)]
acc_wide[, DIO2_selectivity := cytomed - pmin(DIO2_acc, 5)]
acc_wide[, DIO3_selectivity := cytomed - pmin(DIO3_acc, 5)]
acc_wide[, IYD_selectivity := cytomed - pmin(IYD_acc, 5)]
acc_wide[, max_selectivity := pmax(DIO1_selectivity, DIO2_selectivity, DIO3_selectivity, IYD_selectivity, na.rm = T)]

Figure 5 of Truong et al. 

sig.chemotypes <- rownames(M.active[rs.active == 4, ])
tp.sub <- as.data.frame(toxprints[, c("DTXSID", ..sig.chemotypes)])
rownames(tp.sub) <- tp.sub$DTXSID
tp.sub <- tp.sub[, -1, drop = FALSE]
tp.sub <- na.omit(tp.sub)

# get chems that have at least one of the enriched chemotypes 
longchainc.chems <- rownames(tp.sub[rowSums(tp.sub) > 0, , drop = FALSE])

# plot the chems with available selectivity (had to be tested in mc)
# most of these are positive but not all 
sel.data <- acc_wide[dsstox_substance_id %in% longchainc.chems, 
                     .(dsstox_substance_id, chnm, DIO1_acc, DIO2_acc, DIO3_acc, IYD_acc, cytomed, max_selectivity)]

sel.m <- melt.data.table(sel.data, 
                         measure.vars = c(paste0(aenm.abbrevs, "_acc"), "cytomed"), 
                         variable.name = "assay", 
                         value.name = "acc")

sel.m <- sel.m[!is.na(acc)]
sel.m <- sel.m[order(-max_selectivity, -chnm)]

# standardize themes 
my_theme <- theme_bw() +
  theme(axis.text = element_text(size = 10),
        legend.text = element_text(size = 10))

# SELECTIVITY DOTPLOT
dotplot <- ggplot(data = sel.m, 
       mapping = aes(x = reorder(chnm,max_selectivity), 
                     y = acc)) +
  geom_point(aes(color = assay, shape = assay), 
             alpha = 0.8, 
             size = 2.5) +
  scale_shape_manual(values = c("DIO1_acc" = 16, "DIO2_acc" = 16, 
                                "DIO3_acc" = 16, "IYD_acc" = 16,
                                "cytomed" = 8)) +
  annotate("rect", xmin = sel.m[max_selectivity < 0.3][1, chnm],
           xmax = tail(sel.m[max_selectivity < 0.3], n = 1)[, chnm],
           ymin = floor(min(sel.m$acc)), ymax = ceiling(max(sel.m$acc)),
           alpha = .1, fill = "red") +
  my_theme + 
  labs(x = 'Chemical', 
       y = bquote(Concentration ~ at ~ "Threshold ("*log[10]~ mu*"M)")) +
  coord_flip()

# how many of these chems were tested within each assay?
totals.by.assay <- merged_dat[dsstox_substance_id %in% longchainc.chems, 
                     .(total = length(unique(dsstox_substance_id))), by = assay]

testedChems.by.assay <- lapply(aenm.abbrevs, function(ae) {
  merged_dat[assay == ae & dsstox_substance_id %in% longchainc.chems, dsstox_substance_id]
})
names(testedChems.by.assay) <- aenm.abbrevs

# VENN DIAGRAM OF SUBSTANCES WITH CHEMOTYPE THAT WERE TESTED
venn_obj <- ggvenn(testedChems.by.assay, 
       show_percentage = FALSE, 
       fill_color = c("#999999", "#E69F00", "#56B4E9", "#009E73"),
       stroke_linetype = "blank", 
       text_size = 4,
       set_name_size = 3.8) +
  scale_y_continuous(expand = expansion(mult = .1)) # fix labels cropped at the top with this ggplot trick

# class x hitc distribution of these chems 
actives <- merged_dat[dsstox_substance_id %in% longchainc.chems & hitc == 1, 
  .(count = length(unique(dsstox_substance_id))), 
  by = .(assay, class_type, chosen_class)]
actives[, hitcall := "active"]

inactives <- merged_dat[dsstox_substance_id %in% longchainc.chems & hitc == 0, 
  .(count = length(unique(dsstox_substance_id))), 
  by = .(assay, class_type, chosen_class)]
inactives[, hitcall := "inactive"]

class.hitc.dist <- setDT(bind_rows(actives, inactives))

# add stats pertaining to each assay
for (i in 1:length(h.deiod.aenm)) {
  class.hitc.dist[assay == aenm.abbrevs[i], `:=` (
    Nactives = hitc.dist[aenm == h.deiod.aenm[i] & hitc == 1, numChems], # total num of actives in that assay
    Ninactives = hitc.dist[aenm == h.deiod.aenm[i] & hitc == 0, numChems], # total num of inactives in that assay
    Nchemotypes = totals.by.assay[assay == aenm.abbrevs[i], total] # total num of chems described by the chemotypes of interest in each assay
)]}

class.hitc.dist[hitcall == "active", `:=` (pct = (count/Nactives)*100, 
                                    pct_of_Nchemotypes = (count/Nchemotypes)*100
)]

class.hitc.dist[hitcall == "inactive", `:=` (pct = (count/Ninactives)*100, 
                                    pct_of_Nchemotypes = (count/Nchemotypes)*100
)]
class.hitc.dist <- class.hitc.dist[order(-pct_of_Nchemotypes), .SD, keyby = .(assay, hitcall)]

# CLASS DISTRIBUTION OF CHEMS WITH CHEMOTYPE(S)
barchart <- ggplot(class.hitc.dist, 
       aes(x= reorder(chosen_class, pct_of_Nchemotypes),  
           y=pct_of_Nchemotypes, fill=chosen_class)) +
  geom_bar(stat="identity") +
  my_theme +
  theme(legend.position = "none", 
       plot.title.position = "plot", 
       plot.title = element_text(hjust = 0.15, vjust = 0.6)) +
  coord_flip() +
  facet_grid(hitcall ~ assay, scales = "free_y") +
  labs(x = "Class", 
       y = "% of Chemicals with Given Chemotype(s) found Active or Inactive for Target", 
       title = "Class Distribution of Chemicals with chain:alkaneLinear_C(8,10,12,14) chemotype")

class.hitc.dist[hitcall == "active", total_pct := sum(pct), by = assay]

pct.of.actives.per.assay <- unique(class.hitc.dist[!is.na(total_pct), .(total_pct, assay)])
pct.of.actives.per.assay[, in_group := T]

other.actives <- pct.of.actives.per.assay %>% 
  arrange(assay) %>%
  mutate(total_pct = 100-total_pct, 
         in_group = FALSE)

active.pie <- rbind(pct.of.actives.per.assay, other.actives)

# compute the position of labels
active.pie <- active.pie %>% 
  arrange(assay, desc(in_group)) %>%
  mutate(ypos = cumsum(total_pct)- 0.5*total_pct)

# % OF ACTIVES AS A PIECHART 
piechart <- ggplot(active.pie, 
                   aes(x="", y=total_pct, fill = in_group)) +
  geom_bar(stat="identity", width = 1, color = "black") +
  coord_polar("y", start=0) +
  ylim(0, 100) +
  scale_fill_discrete(name = "", 
                      labels = c("Actives not represented by chemotypes", "Actives represented by chemotypes")) +
  facet_wrap(~ assay, nrow =  1) +
  geom_text(aes(x = 1.25, label = ifelse(in_group, paste0(round(total_pct), "%"), "")),
            color = "black", size = 13/.pt, 
            position = position_stack(vjust = 0.5)) +
  theme_void() + 
  theme(legend.position = "bottom",
        legend.text = element_text(size = 12), 
        text = element_text(size = 14), 
        plot.margin = unit(c(1,0.5,0,0.5), "lines")) 

aplusb <- plot_grid(piechart, NULL, venn_obj, rel_heights = c(1,1,1), 
                    rel_widths = c(0.7, 0.05, 0.3),
                    nrow = 1, 
                    labels = c("A", "B"), 
                    label_x = 0, label_y = 0.8, label_size = 20)

cplusd <- plot_grid(barchart, dotplot, rel_heights = c(1.4, 1), 
                    rel_widths = c(1, 0.5), 
                    nrow = 2, 
                    labels = c("C", "D"), 
                    label_x = 0, label_y = 1, label_size = 20)

fig <- plot_grid(aplusb, cplusd,
          rel_heights = c(0.2, 0.8), rel_widths = c(1,1), nrow = 2)

fig

ggsave(plot = fig, 
       units = "in", 
       dpi = 300, 
       width = 10, height = 19, 
       device = "tiff", 
       filename = "./figures/300dpi/longchainc_panactive.tiff")

ggsave(plot = fig, 
       units = "in", 
       dpi = 300, 
       width = 10, height = 19, 
       device = "png", 
       filename = "./figures/longchainc_panactive.png")

# save to RData for later processing 
# save(longchainc.chems,
#      M.hitc,
#      classified_dt,
#      file = "./data/invitrodb_v3_5_deiod_Enrichment.RData")

function to make plots for each ToxPrint grouping

make_plots <- function(chemotypes, piechart.actives = T) {
  tp.sub <- as.data.frame(toxprints[, c("DTXSID", ..chemotypes)])
  rownames(tp.sub) <- tp.sub$DTXSID
  tp.sub <- tp.sub[, -1, drop = FALSE]
  tp.sub <- na.omit(tp.sub)
  
  # get chems that have at least one of the enriched chemotypes 
  chems <- rownames(tp.sub[rowSums(tp.sub) > 0, , drop = FALSE])
  
  # plot the chems with available selectivity (had to be tested in mc)
  # most of these are positive but not all 
  sel.data <- acc_wide[dsstox_substance_id %in% chems, 
                       .(dsstox_substance_id, chnm, DIO1_acc, DIO2_acc, DIO3_acc, IYD_acc, cytomed, max_selectivity)]
  
  sel.m <- melt.data.table(sel.data, 
                           measure.vars = c(paste0(aenm.abbrevs, "_acc"), "cytomed"), 
                           variable.name = "assay", 
                           value.name = "acc")
  
  sel.m <- sel.m[!is.na(acc)]
  sel.m <- sel.m[order(-max_selectivity, -chnm)]
  
  # standardize themes 
  my_theme <- theme_bw() +
    theme(axis.text = element_text(size = 10),
          legend.text = element_text(size = 10))
  
  # SELECTIVITY DOTPLOT
  dotplot <- ggplot(data = sel.m, 
         mapping = aes(x = reorder(chnm,max_selectivity), 
                       y = acc)) +
    geom_point(aes(color = assay, shape = assay), 
               alpha = 0.8, 
               size = 2.5) +
    scale_shape_manual(values = c("DIO1_acc" = 16, "DIO2_acc" = 16, 
                                  "DIO3_acc" = 16, "IYD_acc" = 16,
                                  "cytomed" = 8)) +
    annotate("rect", xmin = sel.m[max_selectivity < 0.3][1, chnm],
             xmax = tail(sel.m[max_selectivity < 0.3], n = 1)[, chnm],
             ymin = floor(min(sel.m$acc)), ymax = ceiling(max(sel.m$acc)),
             alpha = .1, fill = "red") +
    my_theme + 
    labs(x = 'Chemical', y = 'Concentration at Threshold (log uM)') +
    coord_flip()
  
  # how many of these chems were tested within each assay?
  totals.by.assay <- merged_dat[dsstox_substance_id %in% chems, 
                       .(total = length(unique(dsstox_substance_id))), by = assay]
  
  testedChems.by.assay <- lapply(aenm.abbrevs, function(ae) {
    merged_dat[assay == ae & dsstox_substance_id %in% chems, dsstox_substance_id]
  })
  names(testedChems.by.assay) <- aenm.abbrevs
  
  # VENN DIAGRAM OF SUBSTANCES WITH CHEMOTYPE THAT WERE TESTED
  venn_obj <- ggvenn(testedChems.by.assay, 
         show_percentage = FALSE, 
         fill_color = c("#999999", "#E69F00", "#56B4E9", "#009E73"),
         stroke_linetype = "blank", 
         text_size = 4,
         set_name_size = 3.8) +
    scale_y_continuous(expand = expansion(mult = .1))
  
  # class x hitc distribution of these chems 
  actives <- merged_dat[dsstox_substance_id %in% chems & hitc == 1, 
    .(count = length(unique(dsstox_substance_id))), 
    by = .(assay, class_type, chosen_class)]
  actives[, hitcall := "active"]
  
  inactives <- merged_dat[dsstox_substance_id %in% chems & hitc == 0, 
    .(count = length(unique(dsstox_substance_id))), 
    by = .(assay, class_type, chosen_class)]
  inactives[, hitcall := "inactive"]
  
  class.hitc.dist <- setDT(bind_rows(actives, inactives))
  
  # add stats pertaining to each assay
  for (i in 1:length(h.deiod.aenm)) {
    class.hitc.dist[assay == aenm.abbrevs[i], `:=` (
      Nactives = hitc.dist[aenm == h.deiod.aenm[i] & hitc == 1, numChems], # total num of actives in that assay
      Ninactives = hitc.dist[aenm == h.deiod.aenm[i] & hitc == 0, numChems], # total num of inactives in that assay
      Nchemotypes = totals.by.assay[assay == aenm.abbrevs[i], total] # total num of chems described by the chemotypes of interest in each assay
  )]}
  
  class.hitc.dist[hitcall == "active", `:=` (pct = (count/Nactives)*100, 
                                      pct_of_Nchemotypes = (count/Nchemotypes)*100
  )]
  
  class.hitc.dist[hitcall == "inactive", `:=` (pct = (count/Ninactives)*100, 
                                      pct_of_Nchemotypes = (count/Nchemotypes)*100
  )]
  class.hitc.dist <- class.hitc.dist[order(-pct_of_Nchemotypes), .SD, keyby = .(assay, hitcall)]
  
  # CLASS DISTRIBUTION OF CHEMS WITH CHEMOTYPE(S)
  barchart <- ggplot(class.hitc.dist, 
         aes(x= reorder(chosen_class, pct_of_Nchemotypes),  
             y=pct_of_Nchemotypes, fill=chosen_class)) +
    geom_bar(stat="identity") +
    my_theme +
    theme(legend.position = "none", 
         plot.title.position = "plot", 
         plot.title = element_text(hjust = 0.15, vjust = 0.6)) +
    coord_flip() +
    facet_grid(hitcall ~ assay, scales = "free_y") +
    labs(x = "Class", 
         y = "% of Chemicals with Given Chemotype(s) found Active or Inactive for Target", 
         title = "Class Distribution of Chemicals with Chemotype(s)")
  
  if (piechart.actives) {
    class.hitc.dist[hitcall == "active", total_pct := sum(pct), by = assay]
  }
  else {
    class.hitc.dist[hitcall == "inactive", total_pct := sum(pct), by = assay]
  }
  
  pie.per.assay <- unique(class.hitc.dist[!is.na(total_pct), .(total_pct, assay)])
  pie.per.assay[, in_group := T]
  
  other.chunk <- pie.per.assay %>% 
    arrange(assay) %>%
    mutate(total_pct = 100-total_pct, 
           in_group = FALSE)
  
  pie.data <- rbind(pie.per.assay, other.chunk)
  
  # compute the position of labels
  pie.data <- pie.data %>% 
    arrange(assay, desc(in_group)) %>%
    mutate(ypos = cumsum(total_pct)- 0.5*total_pct)
  
  # % OF ACTIVES or INACTIVES AS A PIECHART 
  if (piechart.actives) {
    key.labels <- c("Actives not represented by chemotypes", "Actives represented by chemotypes")
  } else {
    key.labels <- c("Inactives not represented by chemotypes", "Inactives represented by chemotypes")
  }
  piechart <- ggplot(pie.data, 
                     aes(x="", y=total_pct, fill = in_group)) +
    geom_bar(stat="identity", width = 1, color = "black") +
    coord_polar("y", start=0) +
    ylim(0, 100) +
    scale_fill_discrete(name = "", 
                        labels = key.labels) +
    facet_wrap(~ assay, nrow =  1) +
    geom_text(aes(x = 1.25, label = ifelse(in_group, paste0(round(total_pct, digits = 1), "%"), "")),
              color = "black", size = 13/.pt, 
              position = position_stack(vjust = 0.5)) +
    theme_void() + 
    theme(legend.position = "bottom",
          legend.text = element_text(size = 12), 
          text = element_text(size = 14), 
          plot.margin = unit(c(1,0.5,0,0.5), "lines")) 
  
  aplusb <- plot_grid(piechart, NULL, venn_obj, rel_heights = c(1,1,1), 
                      rel_widths = c(0.7, 0.05, 0.3),
                      nrow = 1, 
                      labels = c("A", "B"), 
                      label_x = 0, label_y = 0.8, label_size = 20)
  
  cplusd <- plot_grid(barchart, dotplot, rel_heights = c(1.4, 1), 
                      rel_widths = c(1, 0.5), 
                      nrow = 2, 
                      labels = c("C", "D"), 
                      label_x = 0, label_y = 1, label_size = 20)
  
  fig <- plot_grid(aplusb, cplusd,
            rel_heights = c(0.2, 0.8), rel_widths = c(1,1), nrow = 2)
  
  return(fig)

}

bond:C(_Z)C~Q_a-halocarbonyl (enriched for DIO1-3)

ahalo.res <- make_plots(c("bond:C(~Z)~C~Q_a-halocarbonyl"))
ahalo.res

chain:alkeneLinear_[mono-ene|diene]_* (enriched for DIO1-3)

alk.lin.group <- rownames(M.active[rs.active == 3, ])[3:6]
alk.lin.res <- make_plots(alk.lin.group)
alk.lin.res

bond:CX_halide_alkyl-F_perfluoro_octyl (enriched for DIO1/2/IYD)

halide.res <- make_plots(c("bond:CX_halide_alkyl-F_perfluoro_octyl"))
halide.res

chain:aromaticAlkene_Ph-C2_acyclic_generic (enriched for DIO2/3/IYD)

arom.alk.res <- make_plots(c("chain:aromaticAlkene_Ph-C2_acyclic_generic"))
arom.alk.res

chain:aromaticAlkane_Ph-C6 (enriched for DIO1/2/IYD)

arom.alk.c6 <- make_plots(c("chain:aromaticAlkane_Ph-C6"))
arom.alk.c6

chain:alkene[Branch|Linear]mono-ene* (enriched for DIO2/3)

mono.ene.group <- rownames(M.active[rs.active == 2, ])[4:6]
mono.ene.res <- make_plots(mono.ene.group)
mono.ene.res

chain:aromaticAlkene_Ph-C2_(styrene)* (enriched for DIO2/3)

ring.ph.c2 <- rownames(M.active[rs.active == 2, ])[10:11]
ring.phc2.res <- make_plots(ring.ph.c2)
ring.phc2.res

bond:quatN_alkyl_acyclic (enriched for DIO1/IYD)

quatN.res <- make_plots(c("bond:quatN_alkyl_acyclic"))
quatN.res

bond:CC(=O)C_ketone_alkene_cyclic_3-en-1-one (enriched for DIO1/3)

ketone.alk.res <- make_plots(c("bond:CC(=O)C_ketone_alkene_cyclic_3-en-1-one"))
ketone.alk.res

chain:aromaticAlkane_[Ar|Ph]-C(1)*-[Ar|Ph] (enriched for DIO2/IYD)

arom.alk.xcx.group <- rownames(M.active[rs.active == 2, ])[7:8]
arom.alk.XCX.res <- make_plots(arom.alk.xcx.group)
arom.alk.XCX.res

chain:alkaneLinear_hexadecyl_C16 (enriched for DIO2/IYD)

longc16.res <- make_plots("chain:alkaneLinear_hexadecyl_C16")
longc16.res

Enriched just for DIO1

bond:CC(=O)C_ketone_aromatic_aliphatic

ketone.dio1.res <- make_plots(c("bond:CC(=O)C_ketone_aromatic_aliphatic"))
ketone.dio1.res

bond:[CO(C|H)][ether|alcohol][alkenyl|alkene]_*

alcoh.ethers <- rownames(subset(M.active, DIO1 == 1 & DIO2 == 0 & DIO3 == 0 & IYD == 0))[2:4]

alcohol.res <- make_plots(alcoh.ethers)
alcohol.res

bond:[CS|P_S|SN]_[sulfide|generic]

bonds.w.sulfur <- rownames(subset(M.active, DIO1 == 1 & DIO2 == 0 & DIO3 == 0 & IYD == 0))[c(5,7,8)]

sulfur.res <- make_plots(bonds.w.sulfur)
sulfur.res

ring:hetero_[6_6]O_benzopyrone(1_4-)

ring.dio1.res <- make_plots(c("ring:hetero_[6_6]_O_benzopyrone_(1_4-)", "ring:hetero_[6_6]_O_benzopyran"))
ring.dio1.res

bond:P=O_phosphate_thioate

thioate.res <- make_plots(c("bond:P=O_phosphate_thioate"))
thioate.res

DIO2

chain:alkeneLinear_diene_1_4-diene

chain.dio2.res <- make_plots(c("chain:alkeneLinear_diene_1_4-diene"))
chain.dio2.res

DIO3

Carbonyls

carbonyls <- c("bond:C=O_carbonyl_ab-unsaturated_aliphatic_(michael_acceptors)", 
               "bond:CC(=O)C_ketone_alkene_generic", 
               "chain:alkeneCyclic_ethene_C_(connect_noZ)")

carbonyl.res <- make_plots(carbonyls)
carbonyl.res

Cyclohexenes

cyclohexenes <- c("bond:CC(=O)C_ketone_alkene_cyclic_(C6)", 
                  "chain:alkeneCyclic_diene_cyclohexene")

cyclohex.res <- make_plots(cyclohexenes)
cyclohex.res

bond:CN_amine_sec-NH_aromatic_aliphatic

amine.res <- make_plots(c("bond:CN_amine_sec-NH_aromatic_aliphatic"))
amine.res

ring:hetero_[6]N_triazine(1_3_5-)

triazine.res <- make_plots(c("ring:hetero_[6]_N_triazine_(1_3_5-)"))
triazine.res

bond:CS_sulfide_di-

disulfur.res <- make_plots("bond:CS_sulfide_di-")
disulfur.res

IYD

Halides

halides <- rownames(subset(M.active, DIO1 == 0 & DIO2 == 0 & DIO3 == 0 & IYD == 1))[c(4,5,8,9)]
halide.iyd.res <- make_plots(halides)
halide.iyd.res

bond:CX_halide_alkyl-Cl_dichloro_(1_1-)

dichloro.res <- make_plots(c("bond:CX_halide_alkyl-Cl_dichloro_(1_1-)"))
dichloro.res

## bond:CX_halide_alkyl-F_perfluoro_hexyl

perfluoro.res <- make_plots("bond:CX_halide_alkyl-F_perfluoro_hexyl")
perfluoro.res

bond:COH_alcohol_aromatic_[phenol]*

alcoh.arom.res <- make_plots(c("bond:COH_alcohol_aromatic", 
                               "bond:COH_alcohol_aromatic_phenol"))
alcoh.arom.res

bond:N=N_azo_[aromatic|generic]

azo.res <- make_plots(c("bond:N=N_azo_aromatic", 
                        "bond:N=N_azo_generic"))
azo.res

bond:QQ(Q~O_S)_sulfur_oxide

sulf.oxide.res <- make_plots(c("bond:QQ(Q~O_S)_sulfur_oxide"))
sulf.oxide.res

bond:S(=O)_sulfon^

sulfons <- rownames(subset(M.active, DIO1 == 0 & DIO2 == 0 & DIO3 == 0 & IYD == 1))[13:15]

sulfon.res <- make_plots(sulfons)
sulfon.res

sulfonic Esters

sulf.esters <- rownames(subset(M.active, DIO1 == 0 & DIO2 == 0 & DIO3 == 0 & IYD == 1))[16:18]

sulf.est.res <- make_plots(sulf.esters)
sulf.est.res

ring:fused_[6_6]_naphthalene

db.ring <- make_plots(c("ring:fused_[6_6]_naphthalene"))
db.ring

bond:quatN_generic

quat.res <- make_plots("bond:quatN_generic")
quat.res

bond:C=N_imine_N(connect_noZ)

imine.res <- make_plots("bond:C=N_imine_N(connect_noZ)")
imine.res

Inactives

bond:COH_alcohol_pri-alkyl

dio1.inactive <- make_plots(c("bond:COH_alcohol_pri-alkyl"), piechart.actives = F)
dio1.inactive

how many of these chems have the enriched chemotypes for actives?

enriched.active.ct <- c("chain:alkaneLinear_decyl_C10", 
                        "chain:alkaneLinear_dodedyl_C12", 
                        "chain:alkaneLinear_octyl_C8", 
                        "chain:alkaneLinear_tetradecyl_C14", 
                        "chain:alkeneBranch_mono-ene_2-butene", 
                        "chain:alkeneLinear_mono-ene_allyl", 
                        "chain:alkeneLinear_mono-ene_ethylene_generic")

chain:oxy-alkaneLinear_ethyleneOxide_EO1

dio3.inactive <- make_plots(c("chain:oxy-alkaneLinear_ethyleneOxide_EO1"), 
                            piechart.actives = F)

## Warning in min(sel.m$acc): no non-missing arguments to min; returning Inf

## Warning in max(sel.m$acc): no non-missing arguments to max; returning -Inf

## Warning: No shared levels found between `names(values)` of the manual scale and the
## data's shape values.

dio3.inactive

sessionInfo()

## R version 4.4.1 (2024-06-14 ucrt)
## Platform: x86_64-w64-mingw32/x64
## Running under: Windows 11 x64 (build 22631)
## 
## Matrix products: default
## 
## 
## locale:
## [1] LC_COLLATE=English_United States.utf8 
## [2] LC_CTYPE=English_United States.utf8   
## [3] LC_MONETARY=English_United States.utf8
## [4] LC_NUMERIC=C                          
## [5] LC_TIME=English_United States.utf8    
## 
## time zone: America/New_York
## tzcode source: internal
## 
## attached base packages:
## [1] grid      stats     graphics  grDevices utils     datasets  methods  
## [8] base     
## 
## other attached packages:
##  [1] readxl_1.4.3       openxlsx_4.2.6.1   ggpubr_0.6.0       scales_1.3.0      
##  [5] colorspace_2.1-1   RColorBrewer_1.1-3 viridis_0.6.5      viridisLite_0.4.2 
##  [9] cowplot_1.1.3      ggvenn_0.1.10      ggrepel_0.9.5      ggplot2_3.5.1     
## [13] tidyr_1.3.1        dplyr_1.1.4        data.table_1.16.2  knitr_1.48        
## 
## loaded via a namespace (and not attached):
##  [1] sass_0.4.9        utf8_1.2.4        generics_0.1.3    rstatix_0.7.2    
##  [5] stringi_1.8.4     digest_0.6.36     magrittr_2.0.3    evaluate_1.0.0   
##  [9] fastmap_1.2.0     cellranger_1.1.0  jsonlite_1.8.8    zip_2.3.1        
## [13] backports_1.5.0   gridExtra_2.3     purrr_1.0.2       fansi_1.0.6      
## [17] textshaping_0.4.0 jquerylib_0.1.4   abind_1.4-5       cli_3.6.3        
## [21] rlang_1.1.4       munsell_0.5.1     withr_3.0.2       cachem_1.1.0     
## [25] yaml_2.3.10       tools_4.4.1       ggsignif_0.6.4    broom_1.0.6      
## [29] vctrs_0.6.5       R6_2.5.1          lifecycle_1.0.4   car_3.1-2        
## [33] ragg_1.3.2        pkgconfig_2.0.3   pillar_1.9.0      bslib_0.8.0      
## [37] gtable_0.3.6      glue_1.7.0        Rcpp_1.0.13-1     systemfonts_1.1.0
## [41] highr_0.11        xfun_0.46         tibble_3.2.1      tidyselect_1.2.1 
## [45] rstudioapi_0.16.0 farver_2.1.2      htmltools_0.5.8.1 labeling_0.4.3   
## [49] rmarkdown_2.28    carData_3.0-5     compiler_4.4.1